© 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 Local
    9. 6-RES_SCL-AJT
    11. 31116
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, including names and titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    578
    +0.13
    0.8%
    238
    +0.12
    0.7%
    127
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.13
    0.25
    138
    +0.12
    0.23
    64
    +0.11
    -0.22
    Negative Logits
    oard
    -0.80
    er
    -0.73
    erent
    -0.64
    bags
    -0.63
    bag
    -0.63
    size
    -0.61
    aign
    -0.59
    spring
    -0.59
    ers
    -0.58
    ere
    -0.57
    POSITIVE LOGITS
    loo
    0.81
    çīĪ
    0.69
    onto
    0.64
    hod
    0.63
    senal
    0.62
    ologne
    0.60
    burgh
    0.59
    ya
    0.59
    hiba
    0.58
    rimination
    0.58
    Activations Density 10.377%

    No Known Activations