© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1131
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, such as commands, platforms, and devices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    730
    +0.20
    0.7%
    446
    +0.16
    0.6%
    430
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.20
    0.04
    730
    +0.16
    0.05
    76
    +0.15
    0.05
    Negative Logits
     winters
    -0.84
    heast
    -0.83
     additives
    -0.82
     Chao
    -0.81
     condom
    -0.81
     fragrance
    -0.78
     signatures
    -0.78
     additive
    -0.75
    theless
    -0.75
    glomer
    -0.74
    POSITIVE LOGITS
    mast
    1.23
    antage
    1.07
    oma
    0.96
    ZI
    0.95
    rius
    0.92
    elia
    0.92
    raction
    0.89
    fee
    0.87
    akura
    0.86
     apiece
    0.85
    Activations Density 0.682%

    No Known Activations