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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 2887
    Prev
    Next
    INDEX
    Explanations

    images or pictures identified by numbers in their captions

    oai_token-act-pair · gpt-3.5-turbo

    references to images or photographs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sake
    -0.61
    ually
    -0.59
     unheard
    -0.58
    nia
    -0.57
    *,
    -0.55
    #$
    -0.55
     typh
    -0.52
    agog
    -0.52
     Wonderland
    -0.51
    rugged
    -0.51
    POSITIVE LOGITS
     Caption
    0.93
     Thumbnails
    0.74
    ourke
    0.70
    iframe
    0.65
     ï
    0.63
    vertisements
    0.63
    ensor
    0.62
    anyon
    0.61
    ategories
    0.61
     copyright
    0.58
    Activations Density 0.027%

    No Known Activations