© 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. 11-RES-JB
    11. 1987
    Prev
    Next
    INDEX
    Explanations

    code syntax and snippets

    oai_token-act-pair · gpt-3.5-turbo

    mathematical or coding operations and state transitions

    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
    âĢ
    -0.95
     âĢ
    -0.81
     ðŁij
    -0.73
    »
    -0.72
    îĢ
    -0.69
    âĻ¦
    -0.69
    âĺ
    -0.68
     âĹ
    -0.68
    ãĢ
    -0.67
    âģ
    -0.66
    POSITIVE LOGITS
     alike
    0.67
     everywhere
    0.55
     locals
    0.55
    AME
    0.54
    xious
    0.51
     versa
    0.51
     interchange
    0.50
     hither
    0.49
     wills
    0.49
     respectively
    0.49
    Activations Density 1.141%

    No Known Activations