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 Local
    5. 6-RES_SCL-AJT
    6. 34065
    Prev
    Next
    INDEX
    Explanations

    mentions of time measurements and frequency

    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
    +0.16
    0.8%
    685
    +0.11
    0.5%
    185
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.32
    375
    +0.11
    0.06
    283
    +0.10
    -0.00
    Negative Logits
     Examiner
    -0.63
    eele
    -0.61
    sonian
    -0.61
     Clothing
    -0.60
     liner
    -0.60
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.60
     *)
    -0.60
    ļéĨĴ
    -0.58
     Journals
    -0.56
    leeve
    -0.56
    POSITIVE LOGITS
     consecut
    0.81
    enos
    0.73
     sidx
    0.71
    fect
    0.70
    fts
    0.65
    ciating
    0.64
     advis
    0.63
     attempted
    0.62
    athi
    0.62
     cycles
    0.61
    Activations Density 18.241%

    No Known Activations