© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39705
    Prev
    Next
    INDEX
    Explanations

    statements with contradicting information

    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
    29
    +0.13
    0.7%
    288
    +0.10
    0.5%
    578
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.13
    0.09
    582
    +0.10
    0.06
    326
    +0.09
    0.21
    Negative Logits
     clothed
    -0.61
     Alleg
    -0.58
     Siber
    -0.56
    ============
    -0.56
    xual
    -0.56
     Totem
    -0.56
     Petroleum
    -0.55
    tto
    -0.55
    gaard
    -0.54
    fet
    -0.52
    POSITIVE LOGITS
    icago
    1.07
    anical
    1.01
    amber
    0.89
    arma
    0.88
    ambers
    0.86
    craft
    0.83
    anooga
    0.82
    nown
    0.76
    ronics
    0.76
    ronic
    0.75
    Activations Density 7.890%

    No Known Activations