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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 21114
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Crit" or "Criticism"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Criterion Collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orthy
    -0.86
    noon
    -0.73
    velt
    -0.71
    loo
    -0.68
    owship
    -0.64
     Aad
    -0.63
    heed
    -0.61
    UTH
    -0.60
     Gardens
    -0.59
     Argent
    -0.59
    POSITIVE LOGITS
    erion
    1.38
    ique
    1.22
    icism
    1.22
    iques
    1.17
    ically
    1.09
    iqu
    1.01
    eria
    0.94
    hetically
    0.88
    ters
    0.84
    icals
    0.84
    Activations Density 0.042%

    No Known Activations