© 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. 32162
    Prev
    Next
    INDEX
    Explanations

    computer programming code snippets and related technical 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
    447
    +0.16
    0.7%
    50
    +0.12
    0.5%
    41
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.34
    193
    +0.12
    0.13
    673
    +0.12
    0.11
    Negative Logits
    ascript
    -0.92
    theless
    -0.78
    ilial
    -0.76
    PsyNetMessage
    -0.72
    Versions
    -0.67
    catentry
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.64
    âĸ¬
    -0.64
    phia
    -0.60
    phony
    -0.59
    POSITIVE LOGITS
     Lumpur
    0.96
    EStreamFrame
    0.93
    EStream
    0.79
    ikuman
    0.79
    bye
    0.78
    wagen
    0.72
    enei
    0.72
    utra
    0.71
    ĪĴ
    0.69
    ulu
    0.67
    Activations Density 25.764%

    No Known Activations