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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 259
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jane Austen"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    52
    +0.13
    0.5%
    124
    +0.11
    0.4%
    376
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.08
    232
    +0.11
    0.06
    659
    +0.11
    0.06
    Negative Logits
    orescent
    -1.07
    idy
    -0.90
    orescence
    -0.84
    utations
    -0.81
    seq
    -0.79
    idious
    -0.78
     hypoc
    -0.78
    rophic
    -0.78
    ulative
    -0.77
    acity
    -0.77
    POSITIVE LOGITS
     Doe
    1.24
    Jane
    1.08
    ju
    0.94
    ::::::::
    0.92
    ãĤ©
    0.92
    izable
    0.89
    ufact
    0.87
    knife
    0.85
    vous
    0.85
    ably
    0.83
    Activations Density 1.065%

    No Known Activations