© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2825
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogues containing emotional expressions and personal reflections

    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
    393
    +0.25
    1.0%
    55
    +0.14
    0.6%
    640
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.25
    0.11
    8
    +0.14
    0.08
    110
    +0.12
    0.08
    Negative Logits
    ESE
    -0.79
    onent
    -0.77
    INST
    -0.75
    soever
    -0.74
    aphael
    -0.73
    rence
    -0.72
    iatus
    -0.72
    volent
    -0.71
    izes
    -0.71
    velop
    -0.70
    POSITIVE LOGITS
     gonna
    1.43
     gotta
    1.32
     been
    1.31
     got
    1.19
     supposed
    1.14
     not
    1.11
     gotten
    1.11
     unclear
    1.05
     worth
    1.04
    been
    1.04
    Activations Density 1.158%

    No Known Activations