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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3991
    Prev
    Next
    INDEX
    Explanations

    contradictory statements or 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
    447
    +0.23
    1.3%
    160
    +0.10
    0.6%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.23
    0.10
    526
    +0.10
    -0.09
    195
    +0.10
    -0.02
    Negative Logits
    emetery
    -0.70
    lov
    -0.69
    iatrics
    -0.69
    ubis
    -0.66
    ourning
    -0.64
    dain
    -0.63
    llular
    -0.61
    ixtape
    -0.61
    gins
    -0.61
    fare
    -0.60
    POSITIVE LOGITS
     contradictory
    0.78
     conflicting
    0.72
     viewpoints
    0.71
     substant
    0.70
     contradictions
    0.68
     contradict
    0.66
    xual
    0.65
     juxtap
    0.63
     sexes
    0.60
     sides
    0.59
    Activations Density 11.198%

    No Known Activations