© 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. 31365
    Prev
    Next
    INDEX
    Explanations

    mentions of the web browser "Firefox" and its different versions

    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
    288
    +0.11
    0.6%
    496
    +0.11
    0.6%
    447
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.11
    0.06
    326
    +0.11
    0.20
    368
    +0.11
    0.10
    Negative Logits
    é¾įåĸļ士
    -0.68
    mate
    -0.68
    cious
    -0.66
    sheets
    -0.66
    ioxide
    -0.65
    currency
    -0.63
    cision
    -0.63
    cession
    -0.63
    material
    -0.62
    gra
    -0.61
    POSITIVE LOGITS
    xtap
    0.71
    vernment
    0.69
    ĺħ
    0.68
     blazing
    0.66
     Firefox
    0.62
    awaru
    0.61
    arez
    0.59
    lda
    0.58
    adish
    0.55
     browsers
    0.55
    Activations Density 7.501%

    No Known Activations