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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16903
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of authenticity and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rower
    -0.74
    ulhu
    -0.71
    deen
    -0.70
    zar
    -0.68
    asus
    -0.67
    endment
    -0.63
    utenant
    -0.63
    ¬¼
    -0.63
    gow
    -0.63
    ynthesis
    -0.62
    POSITIVE LOGITS
     ones
    1.56
     creations
    1.05
     inventions
    0.98
     reminders
    0.96
     versions
    0.95
     equivalents
    0.93
     originals
    0.93
     replacements
    0.93
     additions
    0.93
     respectively
    0.92
    Activations Density 0.337%

    No Known Activations