© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4976
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and opposition

    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
    393
    +0.12
    0.8%
    298
    +0.08
    0.6%
    362
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.30
    362
    +0.08
    0.20
    385
    +0.07
    0.21
    Negative Logits
    wcs
    -0.58
    dayName
    -0.50
    strike
    -0.46
    wic
    -0.44
    arily
    -0.44
    .–
    -0.44
    avi
    -0.44
    igue
    -0.43
    externalActionCode
    -0.43
    ucc
    -0.43
    POSITIVE LOGITS
     unsuspecting
    0.53
     mortals
    0.49
     whoever
    0.45
     inexperienced
    0.44
     Ernst
    0.42
    erous
    0.42
     somebody
    0.42
     Ferdinand
    0.42
     beh
    0.42
     oneself
    0.41
    Activations Density 11.152%

    No Known Activations