© 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. 7522
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages and proportions

    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
    worldly
    -0.92
    åĤ
    -0.79
    zie
    -0.78
    ipples
    -0.73
    nings
    -0.72
     Skies
    -0.69
    gest
    -0.68
    bro
    -0.67
    æ©
    -0.67
    andr
    -0.67
    POSITIVE LOGITS
     Invisible
    0.98
     certainty
    0.94
     accuracy
    0.92
     accurate
    0.91
     humidity
    0.86
     completion
    0.84
     pure
    0.79
     chance
    0.79
     confidence
    0.77
     efficient
    0.76
    Activations Density 0.070%

    No Known Activations