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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 4078
    Prev
    Next
    INDEX
    Explanations

    sport-related keywords and phrases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    587
    +0.14
    0.5%
    236
    +0.14
    0.5%
    358
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.14
    0.02
    587
    +0.14
    0.02
    6
    +0.13
    0.02
    Negative Logits
    ministic
    -0.98
    unal
    -0.93
    ding
    -0.92
    eger
    -0.88
    pled
    -0.88
     disgu
    -0.87
    dfx
    -0.86
    ded
    -0.86
    minist
    -0.85
    informed
    -0.84
    POSITIVE LOGITS
    CLOSE
    1.14
    aign
    1.06
    photo
    1.05
     Frazier
    0.99
    Madison
    0.96
     Lansing
    0.95
    IDER
    0.95
    INGTON
    0.91
    MORE
    0.91
     Cincinnati
    0.91
    Activations Density 0.113%

    No Known Activations