© 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. 11-RES-JB
    11. 761
    Prev
    Next
    INDEX
    Explanations

    information about ebook formats and purchasing options

    oai_token-act-pair · gpt-3.5-turbo

    references to downloadable or purchasable digital formats of books and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     streaks
    -0.76
    venge
    -0.76
    76561
    -0.74
     ghosts
    -0.72
     vents
    -0.70
     outl
    -0.70
     [+
    -0.69
    hots
    -0.69
     unforeseen
    -0.68
     explosions
    -0.68
    POSITIVE LOGITS
     PDF
    1.76
     pdf
    1.74
     eBook
    1.62
     ebook
    1.55
     booklet
    1.50
    PDF
    1.49
     paperback
    1.46
    pdf
    1.45
     broch
    1.45
     pamphlet
    1.41
    Activations Density 0.374%

    No Known Activations