© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18347
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities and sports figures

    oai_token-act-pair · gpt-3.5-turbo

    entities or names associated with movies and television content

    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
    iphany
    -0.70
    atos
    -0.65
    izoph
    -0.63
    forcement
    -0.63
    ophob
    -0.61
     sooner
    -0.58
    ocalypse
    -0.58
    angler
    -0.58
    hoe
    -0.57
     exaggeration
    -0.57
    POSITIVE LOGITS
     respectively
    1.01
     apiece
    0.99
    Tickets
    0.95
     Together
    0.89
    Others
    0.87
    Meanwhile
    0.83
    Elsewhere
    0.83
    Both
    0.80
    Former
    0.79
    Together
    0.77
    Activations Density 0.839%

    No Known Activations