© 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. 36841
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Yahoo"

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.17
    0.8%
    288
    +0.15
    0.7%
    99
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.17
    0.10
    269
    +0.15
    0.06
    288
    +0.14
    0.17
    Negative Logits
    nered
    -0.82
    ingham
    -0.82
    ateral
    -0.78
    alez
    -0.77
    iard
    -0.75
    ĸļ
    -0.75
    eele
    -0.74
     Uriel
    -0.73
    ieval
    -0.72
    skirts
    -0.72
    POSITIVE LOGITS
    ahoo
    0.94
    tags
    0.83
     Answers
    0.80
     News
    0.78
     Finance
    0.76
     Sports
    0.75
    conn
    0.75
     View
    0.74
    Talk
    0.73
    !,
    0.71
    Activations Density 6.310%

    No Known Activations