© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 37091
    Prev
    Next
    INDEX
    Explanations

    phrases related to critique, evaluation, or analysis

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.27
    1.2%
    344
    +0.12
    0.6%
    58
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.27
    0.29
    344
    +0.12
    0.21
    157
    +0.12
    0.19
    Negative Logits
    Marg
    -0.73
     srfAttach
    -0.71
    IRT
    -0.70
    Atl
    -0.70
    CHAT
    -0.69
    thia
    -0.69
    EMA
    -0.68
    KEN
    -0.66
    âĵĺ
    -0.65
    ENE
    -0.64
    POSITIVE LOGITS
     technically
    1.00
     ostensibly
    0.88
     initially
    0.76
     theoretically
    0.74
     somewhat
    0.69
     admittedly
    0.66
     undeniably
    0.65
     pid
    0.63
     geographically
    0.63
     physically
    0.62
    Activations Density 26.356%

    No Known Activations