© 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. 18544
    Prev
    Next
    INDEX
    Explanations

    phrases related to size, importance, or ranking

    oai_token-act-pair · gpt-3.5-turbo

    key roles or statuses of entities in various contexts

    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
    ournals
    -0.80
    utics
    -0.79
    Dialogue
    -0.78
    anship
    -0.76
    atism
    -0.75
    oops
    -0.74
     friendships
    -0.73
    ldom
    -0.72
    Rs
    -0.72
     weddings
    -0.72
    POSITIVE LOGITS
     proponent
    1.35
     beneficiary
    1.32
     bidder
    1.27
     source
    1.25
     contributor
    1.24
     supplier
    1.21
    stay
    1.21
     provider
    1.16
     contender
    1.15
     purchaser
    1.13
    Activations Density 0.149%

    No Known Activations