Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19924
    Prev
    Next
    INDEX
    Explanations

    images, illustrations, or artistic representations

    oai_token-act-pair · gpt-3.5-turbo

    references to "drawing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckle
    -0.88
    onte
    -0.83
    ican
    -0.82
    ailability
    -0.81
    ternity
    -0.78
    igmatic
    -0.78
    ricia
    -0.77
    iland
    -0.75
    nown
    -0.74
    colm
    -0.72
    POSITIVE LOGITS
    Artist
    0.90
     Drawing
    0.86
    LIB
    0.86
    Board
    0.82
     drawings
    0.82
     drawing
    0.79
    knife
    0.78
    GGGGGGGG
    0.78
     sketches
    0.77
     pige
    0.74
    Activations Density 0.010%

    No Known Activations