© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4189
    Prev
    Next
    INDEX
    Explanations

    HTML form field elements and attributes

    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
    314
    +0.11
    0.5%
    572
    +0.11
    0.4%
    341
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.10
    373
    +0.11
    -0.11
    684
    +0.10
    0.04
    Negative Logits
    anyahu
    -0.88
     subsequ
    -0.77
    wcs
    -0.77
    soDeliveryDate
    -0.73
    glomer
    -0.73
     Subway
    -0.70
     Institutes
    -0.70
     Wanted
    -0.70
     peripher
    -0.70
    stanbul
    -0.70
    POSITIVE LOGITS
    ========
    0.91
     srfAttach
    0.88
    wered
    0.83
    entry
    0.80
     strutConnector
    0.79
    CVE
    0.79
    ãĥ´ãĤ¡
    0.78
    ============
    0.78
    о
    0.76
     guiActiveUnfocused
    0.74
    Activations Density 4.055%

    No Known Activations