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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 13901
    Prev
    Next
    INDEX
    Explanations

    Russian Cyrillic characters and Asian characters

    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
    447
    +0.92
    14.7%
    138
    +0.17
    2.7%
    314
    +0.06
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.92
    0.99
    447
    +0.17
    0.98
    64
    +0.06
    -0.01
    Negative Logits
     scrambling
    -0.28
     merit
    -0.27
     boarding
    -0.27
     outreach
    -0.27
     pressures
    -0.26
     embold
    -0.26
     opportunities
    -0.26
     poaching
    -0.26
     sway
    -0.26
     temperament
    -0.26
    POSITIVE LOGITS
    N
    0.36
    E
    0.35
    T
    0.34
    Unit
    0.34
    RIP
    0.34
    L
    0.34
    X
    0.34
    G
    0.33
    V
    0.33
    C
    0.33
    Activations Density 1.897%

    No Known Activations