Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13616
    Prev
    Next
    INDEX
    Explanations

    phrases related to trends or patterns, especially in data or society

    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
    +0.25
    1.2%
    160
    +0.16
    0.7%
    288
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.25
    0.11
    608
    +0.16
    0.17
    160
    +0.13
    0.18
    Negative Logits
    gur
    -0.92
    tein
    -0.70
     oath
    -0.68
    vette
    -0.64
     Lak
    -0.62
     jug
    -0.62
     straw
    -0.60
    ×Ļ×
    -0.59
    ÄŁ
    -0.59
    portation
    -0.58
    POSITIVE LOGITS
    setting
    1.17
     trend
    0.97
     Trend
    0.93
     trends
    0.85
    Trend
    0.82
     toward
    0.82
    line
    0.81
    lines
    0.80
    chart
    0.79
     towards
    0.79
    Activations Density 12.634%

    No Known Activations