© 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. 36288
    Prev
    Next
    INDEX
    Explanations

    names of people with the last name "Stevens"

    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
    +0.14
    0.8%
    167
    +0.10
    0.5%
    288
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.14
    0.10
    11
    +0.10
    0.06
    6
    +0.08
    0.15
    Negative Logits
    asta
    -0.66
    izen
    -0.64
    etheless
    -0.63
    theless
    -0.60
    oses
    -0.55
    fully
    -0.55
    otation
    -0.53
    ising
    -0.52
     Seym
    -0.51
     Julio
    -0.49
    POSITIVE LOGITS
    sonian
    0.80
     Stevens
    0.69
    ERSON
    0.58
     Creek
    0.57
    arnaev
    0.56
    burgh
    0.56
    rament
    0.56
    monds
    0.56
    aunders
    0.54
    haw
    0.54
    Activations Density 15.981%

    No Known Activations