© 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. 1386
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating origin or starting point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a range or spectrum of possibilities or variations

    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
    é¾įåĸļ士
    -0.76
     nevertheless
    -0.75
     nonetheless
    -0.71
    orate
    -0.71
    sic
    -0.69
    III
    -0.68
    itone
    -0.67
    Also
    -0.67
    /
    -0.66
     belongs
    -0.66
    POSITIVE LOGITS
     humble
    1.02
     beginner
    1.01
     lowly
    0.97
     beginners
    0.96
     afar
    0.96
     novice
    0.87
     mild
    0.86
     simple
    0.84
     toddlers
    0.84
     cradle
    0.82
    Activations Density 0.110%

    No Known Activations