© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    references to conflicts and clashes

    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
    247
    +0.05
    0.5%
    357
    +0.05
    0.4%
    374
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.05
    0.09
    247
    +0.05
    0.07
    100
    +0.04
    0.08
    Negative Logits
    itect
    -0.35
    ãĥ¼ãĥ«
    -0.35
    matically
    -0.34
    marked
    -0.34
    amy
    -0.34
    imet
    -0.33
    APH
    -0.33
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.33
    apons
    -0.32
    emin
    -0.32
    POSITIVE LOGITS
    ially
    0.42
    iate
    0.41
    channelAvailability
    0.40
    yk
    0.39
    raq
    0.36
    iates
    0.36
    ashtra
    0.36
    HQ
    0.35
    CF
    0.34
    iating
    0.34
    Activations Density 10.864%

    No Known Activations