© 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 EvalsExportsAPI 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. 33750
    Prev
    Next
    INDEX
    Explanations

    words related to being surprised or not expecting a particular outcome

    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
    95
    +0.04
    0.5%
    725
    +0.03
    0.5%
    483
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.04
    0.27
    600
    +0.03
    0.07
    95
    +0.03
    0.05
    Negative Logits
    kay
    -0.20
    ngth
    -0.20
    apt
    -0.19
    apeshifter
    -0.19
    obal
    -0.19
    hesion
    -0.19
    amins
    -0.19
    urai
    -0.18
    itiz
    -0.18
    ©¶æ
    -0.18
    POSITIVE LOGITS
    LER
    0.22
    stakes
    0.20
    swick
    0.19
    Sax
    0.19
     Rate
    0.19
    ATIONS
    0.18
     Dra
    0.18
    inged
    0.18
    LB
    0.18
    052
    0.18
    Activations Density 12.268%

    No Known Activations