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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 7858
    Prev
    Next
    INDEX
    Explanations

    phrases related to film criticism or reviews

    oai_token-act-pair · gpt-3.5-turbo

    references to critiques and critical discussions about film or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loo
    -0.85
    Po
    -0.71
    duino
    -0.71
    keeper
    -0.70
    lda
    -0.69
    shapeshifter
    -0.68
    velt
    -0.68
    posed
    -0.68
    ratom
    -0.67
    ĵĺ
    -0.66
    POSITIVE LOGITS
    erion
    1.12
    icism
    1.04
    icity
    0.98
     Crit
    0.96
    ICAL
    0.85
    ics
    0.84
    ique
    0.83
    ically
    0.82
    icals
    0.75
    ic
    0.74
    Activations Density 0.031%

    No Known Activations