© 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. 9-RES-JB
    11. 13392
    Prev
    Next
    INDEX
    Explanations

    titles or headings in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    emphasis on numerical values and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exha
    -0.83
     favoured
    -0.80
     knockout
    -0.79
     stiff
    -0.77
     drawn
    -0.75
     scrambling
    -0.75
     displacement
    -0.74
     licence
    -0.74
     miniature
    -0.73
     heavyweight
    -0.72
    POSITIVE LOGITS
    âĢ
    1.38
    âĶĢâĶĢâĶĢâĶĢ
    1.32
    https
    1.31
    ________________________________________________________________
    1.27
    Posted
    1.27
    Advertisements
    1.27
    âĶ
    1.26
    http
    1.24
    Trivia
    1.23
    References
    1.23
    Activations Density 0.223%

    No Known Activations