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

    Neuronpedia

    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. 34056
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and codes related to computer programming

    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
    373
    +0.09
    0.7%
    660
    +0.08
    0.6%
    481
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    660
    +0.09
    0.07
    373
    +0.08
    -0.11
    639
    +0.07
    0.08
    Negative Logits
    arov
    -0.48
     Giuliani
    -0.46
    argon
    -0.46
    NRS
    -0.44
    iola
    -0.43
     Bundy
    -0.43
     Blanc
    -0.43
     Noir
    -0.43
     Greene
    -0.42
     Rubin
    -0.41
    POSITIVE LOGITS
    ness
    0.66
     throats
    0.60
    nesses
    0.58
     souls
    0.52
    headed
    0.50
     hump
    0.50
    liest
    0.49
    heart
    0.47
    ening
    0.47
     breaths
    0.46
    Activations Density 3.577%

    No Known Activations