© 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. 36237
    Prev
    Next
    INDEX
    Explanations

    URLs and technical terms related to data transmission and programming languages

    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
    336
    +0.12
    0.5%
    426
    +0.12
    0.5%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.11
    675
    +0.12
    0.14
    308
    +0.11
    0.10
    Negative Logits
     Lans
    -0.71
     Rivera
    -0.70
     Townsend
    -0.68
    boro
    -0.67
     oun
    -0.66
     dise
    -0.64
     Salem
    -0.62
    idious
    -0.61
    ilty
    -0.61
     slips
    -0.60
    POSITIVE LOGITS
    define
    1.18
    !/
    1.16
    ################################
    1.12
    cdn
    1.05
    endif
    0.99
    DIV
    0.95
    âĢİ
    0.93
    AUT
    0.82
    include
    0.82
    MAT
    0.81
    Activations Density 3.828%

    No Known Activations