© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment and surprise

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.17
    0.6%
    151
    +0.15
    0.5%
    691
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.17
    0.06
    195
    +0.15
    0.03
    691
    +0.14
    0.05
    Negative Logits
    amen
    -1.18
    rawled
    -1.06
    ngth
    -1.05
    opic
    -1.05
    tein
    -1.03
    hang
    -1.01
    amins
    -1.00
    bern
    -1.00
    oa
    -0.98
    alach
    -0.98
    POSITIVE LOGITS
     aback
    1.09
    terson
    0.98
     enough
    0.97
    bell
    0.94
     Rampage
    0.92
     about
    0.91
    ãĤ¦ãĤ¹
    0.90
     Gry
    0.88
    cember
    0.88
     bells
    0.87
    Activations Density 0.573%

    No Known Activations