Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4323
    Prev
    Next
    INDEX
    Explanations

    instructions for cooking or baking recipes

    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
    +0.13
    0.6%
    393
    +0.12
    0.5%
    745
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.27
    289
    +0.12
    -0.02
    678
    +0.11
    0.09
    Negative Logits
    Site
    -0.94
    "]=>
    -0.83
     careers
    -0.73
     guiActiveUn
    -0.73
     Limbaugh
    -0.72
    ¥µ
    -0.70
    culosis
    -0.69
    ORPG
    -0.66
     haunt
    -0.65
    ategory
    -0.63
    POSITIVE LOGITS
     vinegar
    1.02
     ingredients
    0.98
     spices
    0.96
     cinnamon
    0.90
     yeast
    0.90
     mixture
    0.89
     melted
    0.87
     garlic
    0.87
     baking
    0.86
     mashed
    0.85
    Activations Density 10.974%

    No Known Activations