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

    Neuronpedia

    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. 14621
    Prev
    Next
    INDEX
    Explanations

    words related to embarrassment and public scrutiny

    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
    640
    +0.18
    0.6%
    201
    +0.18
    0.6%
    526
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.10
    201
    +0.18
    0.06
    326
    +0.15
    0.08
    Negative Logits
    ãĥ¼ãĥ³
    -1.18
    ãĥīãĥ©
    -1.18
    女
    -1.14
    ãĥĥãĥĪ
    -1.13
    姫
    -1.12
    BuyableInstoreAndOnline
    -1.11
    ãĥīãĥ©ãĤ´ãĥ³
    -1.11
     è£ı
    -1.10
    ergic
    -1.04
    wagen
    -1.00
    POSITIVE LOGITS
    edded
    1.67
    odied
    1.63
    arrass
    1.51
    ded
    1.44
    attled
    1.25
    rained
    1.14
    ding
    1.14
    olicy
    1.11
    ed
    1.11
    reon
    1.10
    Activations Density 1.182%

    No Known Activations