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. 8-RES-JB
    6. 21005
    Prev
    Next
    INDEX
    Explanations

    instances of critique or analysis in a comparison to depict struggle or quality

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of films that highlight personal struggles or conflicts

    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
    regulated
    -0.70
    iership
    -0.70
    restricted
    -0.62
     Provision
    -0.61
    cert
    -0.61
    asus
    -0.61
    protected
    -0.60
    eligible
    -0.60
     Volunte
    -0.59
    tax
    -0.58
    POSITIVE LOGITS
     comedic
    1.10
     humorous
    1.04
     jarring
    1.01
     parody
    0.99
     humor
    0.97
     satire
    0.97
     narration
    0.96
     satir
    0.96
     belie
    0.95
     cinematic
    0.94
    Activations Density 1.136%

    No Known Activations