© 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. 10128
    Prev
    Next
    INDEX
    Explanations

    specific patterns related to formatting in textual data, such as headings and bullet points

    oai_token-act-pair · gpt-3.5-turbo

    instances of "UPI" followed by numerical or reference information

    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
    anus
    -0.75
    addafi
    -0.73
    adobe
    -0.69
    heses
    -0.65
    astically
    -0.64
    sis
    -0.63
    astic
    -0.58
    milo
    -0.58
    ¶
    -0.58
    RGB
    -0.58
    POSITIVE LOGITS
    PDATED
    0.74
    ATED
    0.63
     NEXT
    0.61
     filing
    0.61
    Online
    0.58
    \\\\\\\\
    0.57
    NOW
    0.57
    beat
    0.55
     File
    0.54
     twist
    0.54
    Activations Density 0.078%

    No Known Activations