© 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. 31880
    Prev
    Next
    INDEX
    Explanations

    Java programming keywords and 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
    270
    +0.15
    0.6%
    659
    +0.15
    0.6%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.07
    238
    +0.15
    0.06
    564
    +0.13
    0.07
    Negative Logits
     Monstrous
    -0.92
     phyl
    -0.89
     defic
    -0.87
     explan
    -0.84
     cig
    -0.82
     Leia
    -0.81
     submar
    -0.79
    âĸ¬âĸ¬
    -0.79
     cigars
    -0.79
     interf
    -0.78
    POSITIVE LOGITS
    olitan
    1.67
    oleon
    1.65
    ropri
    1.50
    ocalypse
    1.42
    apa
    1.36
    osite
    1.36
    ocalyptic
    1.36
    onent
    1.33
    alm
    1.30
    rison
    1.30
    Activations Density 4.093%

    No Known Activations