© 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. 31401
    Prev
    Next
    INDEX
    Explanations

    political and international affairs mentions, especially related to the presidency and global issues

    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
    +0.12
    0.8%
    393
    +0.08
    0.6%
    549
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.12
    0.23
    608
    +0.08
    0.24
    393
    +0.08
    0.28
    Negative Logits
    ocking
    -0.48
    IPP
    -0.43
    rings
    -0.42
    raq
    -0.41
    eneg
    -0.40
     fingerprints
    -0.40
    ogen
    -0.39
    azor
    -0.39
    istani
    -0.39
    aund
    -0.39
    POSITIVE LOGITS
     arrive
    0.50
     accompany
    0.50
     ensure
    0.49
    ggles
    0.49
     commemorate
    0.46
     Amend
    0.45
     appease
    0.45
     Virtue
    0.45
     explore
    0.45
     become
    0.45
    Activations Density 10.468%

    No Known Activations