© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 31840
    Prev
    Next
    INDEX
    Explanations

    information related to news reports and events happening globally

    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
    +0.29
    1.3%
    195
    +0.15
    0.7%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.29
    0.09
    114
    +0.15
    0.06
    591
    +0.12
    0.04
    Negative Logits
    uit
    -0.74
    antics
    -0.71
    ophers
    -0.70
    arden
    -0.68
     Chamberlain
    -0.68
     bonding
    -0.68
     Nadu
    -0.68
    uits
    -0.68
    ucky
    -0.67
    itational
    -0.67
    POSITIVE LOGITS
    è¦ļéĨĴ
    0.83
     quoting
    0.76
    print
    0.74
     reports
    0.74
    orial
    0.74
    biz
    0.73
     REPORT
    0.73
     relayed
    0.70
     sources
    0.69
    ounces
    0.69
    Activations Density 8.017%

    No Known Activations