© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    descriptive words describing intense, emotional situations or events

    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
    502
    +0.14
    0.5%
    706
    +0.14
    0.5%
    311
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.14
    0.05
    589
    +0.14
    0.05
    311
    +0.13
    0.02
    Negative Logits
    BuyableInstoreAndOnline
    -1.00
     forks
    -0.97
    SPONSORED
    -0.95
     forged
    -0.89
     Tsukuyomi
    -0.88
     ceilings
    -0.83
    HAM
    -0.83
    Cu
    -0.81
     guesses
    -0.79
     SERV
    -0.77
    POSITIVE LOGITS
    abase
    1.57
    rices
    1.39
    ainment
    1.33
    rix
    1.30
    hens
    1.30
    istics
    1.29
    ronics
    1.25
    rium
    1.25
    rain
    1.23
    rition
    1.23
    Activations Density 0.540%

    No Known Activations