© 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. 7882
    Prev
    Next
    INDEX
    Explanations

    expressions related to satisfaction or dissatisfaction

    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
    195
    +0.22
    0.7%
    151
    +0.20
    0.6%
    288
    +0.18
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.22
    0.08
    288
    +0.20
    0.08
    195
    +0.18
    0.03
    Negative Logits
    oss
    -1.10
    pmwiki
    -1.09
    otin
    -0.99
    olan
    -0.99
    umn
    -0.98
    bold
    -0.97
    nature
    -0.95
    egal
    -0.93
    plane
    -0.92
    otta
    -0.91
    POSITIVE LOGITS
    ments
    1.68
    actory
    1.66
    MENTS
    1.36
    ment
    1.32
    atisf
    1.31
    iated
    1.28
     Satisf
    1.28
     satisfied
    1.20
    teness
    1.17
    MENT
    1.15
    Activations Density 0.996%

    No Known Activations