© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    instructions and warnings related to handling and storing items

    oai_token-act-pair · gpt-3.5-turbo

    instructions and warnings related to safety and usage

    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
    albeit
    -0.71
    eret
    -0.70
     ample
    -0.70
     plenty
    -0.67
     manageable
    -0.65
    response
    -0.63
     hopefully
    -0.63
    icion
    -0.63
     terrific
    -0.61
    surprisingly
    -0.61
    POSITIVE LOGITS
     nor
    1.42
     unless
    1.31
     EVER
    1.10
     whatsoever
    1.07
    unless
    1.05
     anymore
    1.05
     ANY
    1.04
     unnecessarily
    0.98
     except
    0.96
     anything
    0.92
    Activations Density 0.558%

    No Known Activations