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. 34141
    Prev
    Next
    INDEX
    Explanations

    technical details related to software development

    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
    +0.31
    1.3%
    527
    +0.10
    0.4%
    343
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.31
    0.09
    229
    +0.10
    0.06
    527
    +0.10
    0.02
    Negative Logits
    ĸļ
    -0.91
     omission
    -0.82
    inki
    -0.78
    ļéĨĴ
    -0.73
    assetsadobe
    -0.64
    ribly
    -0.64
    versible
    -0.63
     looph
    -0.61
    EStream
    -0.60
     cuff
    -0.60
    POSITIVE LOGITS
    rosso
    0.88
     guiActiveUnfocused
    0.82
    itions
    0.72
     guiName
    0.72
    hig
    0.71
    ngth
    0.69
     Sor
    0.69
    âĦ¢:
    0.67
    scl
    0.67
    arten
    0.65
    Activations Density 22.258%

    No Known Activations