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 Local
    5. 6-RES_SCL-AJT
    6. 13507
    Prev
    Next
    INDEX
    Explanations

    names related to ancient myths and folklore

    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
    +0.12
    0.6%
    403
    +0.10
    0.5%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.12
    0.06
    52
    +0.10
    0.06
    649
    +0.10
    0.01
    Negative Logits
     docking
    -0.59
    76561
    -0.57
    âϦ
    -0.55
     recess
    -0.55
    rawdownloadcloneembedreportprint
    -0.55
     Hale
    -0.55
     redress
    -0.54
     defamation
    -0.54
    Charges
    -0.52
     forgiveness
    -0.52
    POSITIVE LOGITS
    opot
    1.10
    ocrates
    0.95
    ey
    0.84
    ocamp
    0.83
    ocratic
    0.82
    oly
    0.82
    ety
    0.80
    olit
    0.79
    eties
    0.78
    erc
    0.75
    Activations Density 8.933%

    No Known Activations