© 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. 300
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and programming keywords, especially related to Swift programming and neural networks

    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
    709
    +0.15
    0.5%
    199
    +0.13
    0.5%
    289
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.11
    326
    +0.13
    0.09
    709
    +0.13
    0.08
    Negative Logits
    gdala
    -1.27
    ividual
    -1.07
    ccording
    -0.99
    hemat
    -0.97
    FORE
    -0.95
     Alive
    -0.94
    iscons
    -0.89
    querque
    -0.89
    undai
    -0.89
    uilding
    -0.89
    POSITIVE LOGITS
    ness
    1.59
    nesses
    1.32
    itude
    1.16
     judgement
    1.15
    wcsstore
    1.09
     judgment
    1.09
    itudes
    1.06
    cliffe
    1.03
    ly
    1.01
    arity
    1.00
    Activations Density 1.198%

    No Known Activations