© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4912
    Prev
    Next
    INDEX
    Explanations

    details of changes and adjustments made in a specific context (such as in-game mechanics or products) by looking for keywords like 'redesigned', 'increased', 'removed', and 'adjusted'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    566
    +0.12
    0.6%
    326
    +0.09
    0.5%
    373
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.11
    8
    +0.09
    0.11
    756
    +0.09
    -0.12
    Negative Logits
    vernment
    -0.70
    educ
    -0.61
    funding
    -0.61
    代
    -0.59
    atform
    -0.58
     taxp
    -0.58
    ãĥ©ãĥ³
    -0.57
    utherford
    -0.56
    illin
    -0.56
    meet
    -0.56
    POSITIVE LOGITS
     abound
    0.86
     optional
    0.68
     suffice
    0.65
    optional
    0.64
     perk
    0.63
     Helpful
    0.63
     unaffected
    0.60
     integral
    0.60
    amas
    0.58
     plentiful
    0.58
    Activations Density 6.817%

    No Known Activations