© 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. 4126
    Prev
    Next
    INDEX
    Explanations

    financial-related terms and names

    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
    63
    +0.09
    0.5%
    248
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.09
    0.07
    4
    +0.09
    0.08
    659
    +0.09
    0.07
    Negative Logits
    ĪĴ
    -0.73
    odan
    -0.71
    schild
    -0.67
    Ë
    -0.64
    FACE
    -0.64
     lull
    -0.64
    ovych
    -0.62
    reality
    -0.62
    lyak
    -0.60
    xual
    -0.59
    POSITIVE LOGITS
    cially
    0.64
    enza
    0.63
    gio
    0.61
     fodder
    0.60
    uala
    0.59
    shed
    0.58
    ruary
    0.58
    reau
    0.57
    thood
    0.56
    elsen
    0.56
    Activations Density 3.007%

    No Known Activations