© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12782
    Prev
    Next
    INDEX
    Explanations

    comparisons between entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating similarity or equivalence

    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
    rower
    -0.89
    oire
    -0.83
    ossession
    -0.82
    erva
    -0.82
    utan
    -0.81
    obook
    -0.81
    alian
    -0.79
    ivism
    -0.77
    section
    -0.74
    endment
    -0.73
    POSITIVE LOGITS
     ambassadors
    1.34
     replacements
    1.31
     pillars
    1.26
     extensions
    1.26
     embodiments
    1.25
     heroes
    1.25
     equivalents
    1.23
     pioneers
    1.23
     losers
    1.20
     icons
    1.20
    Activations Density 0.381%

    No Known Activations