© 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. 33796
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and storytelling in informal language

    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
    447
    +0.28
    1.5%
    326
    +0.10
    0.5%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.28
    0.15
    697
    +0.10
    0.09
    119
    +0.10
    0.13
    Negative Logits
     solitary
    -0.60
    inals
    -0.57
     prost
    -0.54
    urg
    -0.53
    ©¶æ
    -0.53
    prus
    -0.52
     quadru
    -0.51
    adr
    -0.49
     brig
    -0.48
    driving
    -0.47
    POSITIVE LOGITS
     Anyway
    0.74
    Anyway
    0.71
     anyways
    0.71
     ado
    0.67
    adays
    0.65
    ipop
    0.64
     gotta
    0.64
    ymes
    0.63
    ional
    0.62
     lets
    0.61
    Activations Density 11.035%

    No Known Activations