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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13800
    Prev
    Next
    INDEX
    Explanations

    information related to scientific research and statistical methods

    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
    41
    +0.09
    0.5%
    314
    +0.09
    0.5%
    560
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.09
    0.16
    196
    +0.09
    0.05
    14
    +0.09
    0.04
    Negative Logits
     FTC
    -0.62
    xual
    -0.58
     purse
    -0.55
    \/\/
    -0.55
    WORK
    -0.55
     creat
    -0.54
    Catalog
    -0.54
     lockout
    -0.54
     deduction
    -0.54
     certs
    -0.53
    POSITIVE LOGITS
    levard
    1.17
    lehem
    1.14
    apest
    0.95
    mingham
    0.90
    keley
    0.86
    ause
    0.79
    rill
    0.76
    illet
    0.75
    isl
    0.75
    ucha
    0.75
    Activations Density 13.092%

    No Known Activations