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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13175
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "cat"

    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
    167
    +0.19
    0.7%
    447
    +0.14
    0.5%
    549
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.19
    0.06
    167
    +0.14
    -0.04
    527
    +0.13
    0.02
    Negative Logits
    mble
    -0.98
     htt
    -0.91
     Seym
    -0.90
    hower
    -0.83
    gur
    -0.83
     Sacrament
    -0.81
    undo
    -0.81
    indal
    -0.80
     Vaugh
    -0.80
    å¾
    -0.79
    POSITIVE LOGITS
    aclysm
    1.75
    heter
    1.46
    apult
    1.29
    fish
    1.25
    alogue
    1.23
    cher
    1.21
    cat
    1.21
    alyst
    1.17
    hedral
    1.16
    chers
    1.16
    Activations Density 6.933%

    No Known Activations