© 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. 7-RES-JB
    11. 16757
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and HTML tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.74
     demolition
    -0.71
     Ridge
    -0.68
    xual
    -0.68
     Reloaded
    -0.68
     Rus
    -0.68
     Pug
    -0.68
     Berman
    -0.67
     Xue
    -0.65
     Bake
    -0.65
    POSITIVE LOGITS
    div
    1.08
    src
    1.00
    DIV
    0.99
    span
    0.98
    font
    0.95
    fb
    0.93
    register
    0.90
    usr
    0.89
    college
    0.89
    ml
    0.87
    Activations Density 0.011%

    No Known Activations