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. 13346
    Prev
    Next
    INDEX
    Explanations

    information related to medical and scientific trials, such as treatments using stem cells and medical procedures, as well as words related to trials and testing in various contexts

    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
    311
    +0.04
    0.7%
    231
    +0.04
    0.6%
    464
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.04
    0.08
    26
    +0.04
    0.11
    596
    +0.03
    0.07
    Negative Logits
    manship
    -0.25
    icating
    -0.20
     schizophren
    -0.20
     ethic
    -0.20
    heads
    -0.19
     supplies
    -0.19
    sterdam
    -0.19
    lers
    -0.19
    layer
    -0.19
    matically
    -0.18
    POSITIVE LOGITS
    umph
    0.25
    ilee
    0.24
    angles
    0.24
    untary
    0.22
    urnal
    0.22
    angle
    0.22
     Pradesh
    0.22
    ple
    0.22
    PLIC
    0.21
    GI
    0.21
    Activations Density 10.374%

    No Known Activations