© 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. 37191
    Prev
    Next
    INDEX
    Explanations

    references to news and information related to various topics, potentially focusing on political events and media coverage

    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
    447
    +0.13
    0.7%
    420
    +0.09
    0.5%
    503
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.13
    0.08
    167
    +0.09
    -0.04
    195
    +0.08
    -0.01
    Negative Logits
    orney
    -0.66
    avery
    -0.56
    struction
    -0.56
    BuyableInstoreAndOnline
    -0.56
    iphate
    -0.56
    aughs
    -0.55
    elsius
    -0.55
    inho
    -0.53
    ioxide
    -0.52
    asse
    -0.52
    POSITIVE LOGITS
    worthy
    0.80
    flash
    0.75
    reader
    0.69
    worthiness
    0.69
    room
    0.67
     Roundup
    0.63
    letter
    0.60
    print
    0.60
    letters
    0.60
     announcements
    0.58
    Activations Density 9.801%

    No Known Activations