© 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. 22617
    Prev
    Next
    INDEX
    Explanations

    references to figures and scientific data

    oai_token-act-pair · gpt-3.5-turbo

    elements related to scientific figures and data presentation

    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
     Reincarn
    -0.66
    oleon
    -0.66
     lockout
    -0.64
    whatever
    -0.63
    indal
    -0.63
    Anything
    -0.60
     Misty
    -0.60
    ulous
    -0.60
    ebook
    -0.59
    nesota
    -0.59
    POSITIVE LOGITS
     illustrates
    1.24
    Figure
    1.19
     depicts
    1.17
     largeDownload
    1.07
     Figure
    1.05
     illustrating
    1.04
     shows
    1.03
     summarizes
    1.02
     plots
    1.02
    shows
    0.99
    Activations Density 0.069%

    No Known Activations