© 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. 36959
    Prev
    Next
    INDEX
    Explanations

    words related to confrontation and conflict

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    543
    +0.10
    0.5%
    539
    +0.09
    0.5%
    168
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.10
    0.12
    543
    +0.09
    0.11
    589
    +0.08
    0.09
    Negative Logits
    imil
    -0.60
    ortmund
    -0.60
    asma
    -0.59
    ollow
    -0.59
    stract
    -0.58
    ussen
    -0.58
    idelines
    -0.58
    wcs
    -0.57
    olkien
    -0.57
    orsi
    -0.56
    POSITIVE LOGITS
     son
    0.68
     nig
    0.68
     dear
    0.65
    ?!"
    0.62
     Dad
    0.61
     Comet
    0.60
    !?"
    0.60
     mum
    0.57
     daughter
    0.57
     laugh
    0.56
    Activations Density 6.855%

    No Known Activations