© 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
    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. 35411
    Prev
    Next
    INDEX
    Explanations

    mentions of beliefs, thoughts, and speculations

    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%
    493
    +0.12
    0.6%
    542
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.17
    0.07
    70
    +0.12
    0.11
    493
    +0.11
    0.08
    Negative Logits
    Interstitial
    -0.74
    ettlement
    -0.65
    unciation
    -0.64
    ventory
    -0.63
    claimer
    -0.63
    avier
    -0.61
     Jackets
    -0.60
    comes
    -0.59
    mails
    -0.59
    enance
    -0.58
    POSITIVE LOGITS
    ¯
    0.68
    ª
    0.67
    ¶
    0.66
    ril
    0.64
    ocry
    0.63
    ¾
    0.63
     proport
    0.62
     distingu
    0.61
    Ĥİ
    0.61
    DX
    0.60
    Activations Density 8.382%

    No Known Activations