© 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. 9942
    Prev
    Next
    INDEX
    Explanations

    comparisons and quantities mentioned in terms of being more or less

    oai_token-act-pair · gpt-3.5-turbo

    comparative or relative quantities and conditions

    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
     Spit
    -0.65
     Pinball
    -0.64
     Television
    -0.63
     Blueprint
    -0.61
     Bubble
    -0.61
     Writer
    -0.61
     Films
    -0.59
     Journalism
    -0.58
     Writers
    -0.58
    rities
    -0.58
    POSITIVE LOGITS
     restrictive
    1.03
     advantageous
    1.03
     stringent
    1.02
     expensive
    0.95
     severe
    0.91
     preferably
    0.89
     efficient
    0.88
     len
    0.88
     efficiently
    0.87
     costly
    0.86
    Activations Density 0.234%

    No Known Activations