© 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. 31426
    Prev
    Next
    INDEX
    Explanations

    terms related to extending, surpassing, or going beyond conventional boundaries or limits

    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
    447
    +0.20
    0.9%
    57
    +0.12
    0.5%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.20
    0.07
    183
    +0.12
    0.09
    315
    +0.11
    0.05
    Negative Logits
    ICAN
    -0.91
    pmwiki
    -0.79
     WATCHED
    -0.73
    ALLY
    -0.67
    ãĤ·ãĥ£
    -0.67
     Assass
    -0.67
     Mub
    -0.66
    TIME
    -0.66
    Ped
    -0.65
    è¦ļéĨĴ
    -0.65
    POSITIVE LOGITS
     comprehension
    0.82
    esis
    0.79
    ordinary
    0.75
     bounds
    0.74
     Borders
    0.73
     reach
    0.72
    iche
    0.71
     Horizons
    0.70
     ordinary
    0.69
    atos
    0.69
    Activations Density 10.006%

    No Known Activations