© 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 EvalsExportsinterp-engineNEWAPI 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. 7715
    Prev
    Next
    INDEX
    Explanations

    strong emotional content associated with negative actions and their consequences

    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
    299
    +0.17
    0.6%
    204
    +0.16
    0.5%
    639
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.17
    0.07
    639
    +0.16
    0.05
    204
    +0.14
    0.04
    Negative Logits
     lapse
    -0.90
     Florence
    -0.90
    Äĩ
    -0.87
     Jungle
    -0.85
     Tomorrow
    -0.84
    yip
    -0.83
     Kinnikuman
    -0.80
     toug
    -0.80
    inventoryQuantity
    -0.80
    BuyableInstoreAndOnline
    -0.80
    POSITIVE LOGITS
    ption
    1.40
    owship
    1.31
    ction
    1.25
    ointed
    1.22
    akable
    1.12
    abil
    1.06
    xual
    1.05
    LECT
    1.04
    ogyn
    1.02
    lement
    1.01
    Activations Density 0.966%

    No Known Activations