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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35637
    Prev
    Next
    INDEX
    Explanations

    information related to animal welfare issues, slaughtering, and killings

    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
    288
    +0.08
    0.7%
    526
    +0.07
    0.7%
    65
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.21
    288
    +0.07
    0.19
    314
    +0.05
    -0.06
    Negative Logits
     Ronaldo
    -0.36
     fortun
    -0.35
     unlaw
    -0.35
     charism
    -0.35
    aucas
    -0.34
     Tuc
    -0.34
    ioxide
    -0.34
     illum
    -0.34
     Scotia
    -0.34
     validity
    -0.34
    POSITIVE LOGITS
    houses
    0.67
    house
    0.63
    fish
    0.55
     Slaughter
    0.54
    hide
    0.51
    flies
    0.49
    hammer
    0.49
    dogs
    0.46
    ificial
    0.45
    housing
    0.44
    Activations Density 7.840%

    No Known Activations