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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20064
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and financial figures

    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
     whilst
    -1.15
    Âł
    -1.08
    ".[
    -1.06
     Whilst
    -1.01
    !".
    -1.00
    â̦..
    -0.98
    ↵Âł
    -0.96
    ´
    -0.96
     ðŁĻĤ
    -0.95
    "â̦
    -0.94
    POSITIVE LOGITS
     cellphone
    0.88
     lawmakers
    0.70
     Sept
    0.69
     longtime
    0.67
     Tuesday
    0.64
     Legislature
    0.63
     Thursday
    0.63
     Maine
    0.62
     Wednesday
    0.62
     Delaware
    0.62
    Activations Density 1.796%

    No Known Activations