© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 73
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Kenneth" and "Luke"

    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
    311
    +0.25
    0.8%
    326
    +0.19
    0.6%
    316
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.25
    0.13
    288
    +0.19
    0.13
    316
    +0.18
    0.07
    Negative Logits
    atform
    -1.28
    acl
    -1.09
    asted
    -1.03
    gow
    -1.02
    intosh
    -1.01
    oulos
    -0.99
    enegger
    -0.96
    ropolitan
    -0.95
    Agg
    -0.95
    ovember
    -0.93
    POSITIVE LOGITS
    terday
    1.30
    uez
    1.28
    glers
    1.26
    uer
    1.13
    UES
    1.13
    perature
    1.12
    boat
    1.11
    bers
    1.07
    pees
    1.05
    kes
    1.04
    Activations Density 2.282%

    No Known Activations