© 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. 16316
    Prev
    Next
    INDEX
    Explanations

    information or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge and understanding

    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
    itter
    -0.77
    ishers
    -0.68
    ĪĴ
    -0.68
    IRO
    -0.62
    ŃĶ
    -0.61
    adies
    -0.60
    plet
    -0.60
     Mek
    -0.59
    anco
    -0.58
    ishable
    -0.57
    POSITIVE LOGITS
    ledge
    1.03
    lege
    1.01
     intimately
    0.85
     about
    0.80
    ledged
    0.80
     ABOUT
    0.79
     anecd
    0.77
     existed
    0.76
     instinctively
    0.76
    nothing
    0.76
    Activations Density 0.061%

    No Known Activations