© 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. 973
    Prev
    Next
    INDEX
    Explanations

    traits or characteristics related to talents, misbehavior, value, and economic strategies

    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
    712
    +0.13
    0.5%
    167
    +0.12
    0.4%
    616
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.19
    232
    +0.12
    0.10
    325
    +0.11
    0.10
    Negative Logits
    theless
    -1.10
    stellar
    -0.88
    idious
    -0.86
    Ô
    -0.84
    anwhile
    -0.83
    staking
    -0.79
    FUL
    -0.79
    iblical
    -0.76
    uyomi
    -0.76
    ullivan
    -0.76
    POSITIVE LOGITS
    lance
    1.18
    eworks
    1.07
    ials
    1.05
    iors
    1.04
    iffs
    1.04
    istries
    1.03
    ifts
    1.01
    tones
    1.01
    ancies
    1.00
    ifiers
    0.99
    Activations Density 4.565%

    No Known Activations