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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39936
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements

    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
    288
    +0.12
    0.5%
    447
    +0.11
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.17
    526
    +0.11
    -0.04
    208
    +0.11
    0.08
    Negative Logits
    SHIP
    -0.85
    ĪĴ
    -0.77
    ryu
    -0.71
    bis
    -0.68
    \\\\\\\\
    -0.68
    ALLY
    -0.67
    BLIC
    -0.65
    ignty
    -0.65
    DOM
    -0.64
    ntax
    -0.64
    POSITIVE LOGITS
    agne
    1.15
    aic
    1.09
    hetamine
    1.06
    aign
    1.05
    shire
    1.02
    eters
    1.00
    oline
    0.96
    osite
    0.85
    owered
    0.84
    ension
    0.84
    Activations Density 5.290%

    No Known Activations