© 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. 13105
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative human behaviors or characteristics

    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
    503
    +0.11
    0.4%
    383
    +0.11
    0.4%
    131
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.06
    404
    +0.11
    0.06
    406
    +0.11
    0.06
    Negative Logits
    USD
    -0.92
    Lago
    -0.84
     eyebrows
    -0.76
     suspense
    -0.71
    ynthesis
    -0.68
    ynt
    -0.67
     buttocks
    -0.66
    Reviewer
    -0.66
    jun
    -0.66
    ĨĴ
    -0.66
    POSITIVE LOGITS
    ably
    1.14
    nant
    1.08
    antly
    1.03
    rence
    1.01
    ptive
    1.01
    ileged
    1.00
    enment
    0.96
    owship
    0.95
    abil
    0.94
    erences
    0.93
    Activations Density 0.990%

    No Known Activations