© 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. 35358
    Prev
    Next
    INDEX
    Explanations

    contradictory statements or opposing viewpoints in texts

    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
    159
    +0.04
    0.5%
    239
    +0.04
    0.5%
    609
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.04
    0.08
    159
    +0.04
    0.08
    318
    +0.04
    0.07
    Negative Logits
    natureconservancy
    -0.32
    sol
    -0.28
    bil
    -0.27
    etsk
    -0.27
    igsaw
    -0.26
    gres
    -0.26
    iasco
    -0.25
    force
    -0.25
    slave
    -0.25
    hov
    -0.24
    POSITIVE LOGITS
     aside
    0.34
    Correct
    0.32
    nown
    0.31
     obser
    0.30
    Clar
    0.30
    UGH
    0.29
     paraph
    0.29
    Correction
    0.28
     modesty
    0.28
    udos
    0.27
    Activations Density 8.782%

    No Known Activations