© 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. 33187
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations

    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
    339
    +0.13
    0.7%
    195
    +0.10
    0.6%
    316
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.25
    326
    +0.10
    0.23
    709
    +0.10
    0.12
    Negative Logits
    rified
    -0.67
    tle
    -0.63
    о
    -0.62
    hips
    -0.62
    è¦ļéĨĴ
    -0.58
     Acer
    -0.58
    oo
    -0.57
    yll
    -0.57
    te
    -0.56
    izoph
    -0.55
    POSITIVE LOGITS
    itures
    0.66
    vironment
    0.65
    cean
    0.63
    ISSION
    0.62
    ovie
    0.61
    ctor
    0.59
    merce
    0.58
    selage
    0.58
    nington
    0.58
    velop
    0.58
    Activations Density 7.708%

    No Known Activations