© 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. 36976
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and criminal incidents

    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
    481
    +0.14
    0.6%
    447
    +0.13
    0.5%
    585
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.21
    224
    +0.13
    0.10
    346
    +0.12
    0.09
    Negative Logits
    incarn
    -0.90
     ç¥ŀ
    -0.82
    beh
    -0.73
    ||||
    -0.71
    ãĤ¯
    -0.70
     (?,
    -0.69
    spir
    -0.68
    milo
    -0.68
    layer
    -0.68
    discrimination
    -0.67
    POSITIVE LOGITS
     speculate
    0.96
     conclud
    0.92
     concludes
    0.84
     recommends
    0.78
     overlook
    0.76
     theor
    0.75
     calculates
    0.74
     advises
    0.74
     suggests
    0.74
     noted
    0.73
    Activations Density 9.667%

    No Known Activations