© 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. 40811
    Prev
    Next
    INDEX
    Explanations

    adjectives describing various degrees of intensity or severity

    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
    +0.26
    1.1%
    455
    +0.12
    0.5%
    387
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.22
    151
    +0.12
    0.17
    251
    +0.11
    0.10
    Negative Logits
    CHAT
    -0.70
    essler
    -0.69
    Sharp
    -0.67
    SEA
    -0.66
    along
    -0.65
     Glover
    -0.65
    owell
    -0.61
    MS
    -0.60
    avery
    -0.60
    Stars
    -0.59
    POSITIVE LOGITS
     than
    1.89
    than
    1.57
     Than
    1.34
     sounding
    0.92
     versions
    0.83
    erous
    0.82
    iable
    0.79
    iated
    0.79
     pursuits
    0.76
     installments
    0.75
    Activations Density 8.533%

    No Known Activations