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. 4-RES-JB
    6. 19149
    Prev
    Next
    INDEX
    Explanations

    text related to comic book characters and creators

    oai_token-act-pair · gpt-3.5-turbo

    information related to the authors and production details of comics or graphic novels

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

    No Comments

    Negative Logits
    heid
    -0.76
    TPPStreamerBot
    -0.75
     OECD
    -0.74
     statist
    -0.70
    daily
    -0.70
     begg
    -0.70
     econom
    -0.69
    ickr
    -0.68
     homeless
    -0.68
    debian
    -0.67
    POSITIVE LOGITS
     Whedon
    1.01
     Comics
    0.96
     Variant
    0.90
    canon
    0.90
    Marvel
    0.88
     Collider
    0.86
    eatures
    0.85
     Vert
    0.85
     Agents
    0.84
    agonists
    0.82
    Activations Density 0.523%

    No Known Activations