© 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. 31603
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'criticism' or related terms

    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
    8
    +0.12
    0.5%
    178
    +0.11
    0.5%
    640
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.12
    0.10
    314
    +0.11
    -0.03
    326
    +0.11
    0.17
    Negative Logits
    loo
    -0.89
    velt
    -0.87
    orthy
    -0.79
    pora
    -0.73
    holders
    -0.71
    ATTLE
    -0.69
    noon
    -0.68
     Tale
    -0.68
    Leary
    -0.68
     Gardens
    -0.67
    POSITIVE LOGITS
    erion
    1.56
    iques
    1.42
    ique
    1.41
    icism
    1.38
    iqu
    1.28
    eria
    1.17
    ically
    1.11
    icals
    1.07
    iants
    1.00
    osure
    1.00
    Activations Density 4.667%

    No Known Activations