© 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. 6687
    Prev
    Next
    INDEX
    Explanations

    mentions of large scale events or objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large-scale events or quantities

    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
     Nich
    -0.72
    onso
    -0.70
    vous
    -0.68
    emis
    -0.63
    orio
    -0.63
    vice
    -0.63
    herent
    -0.63
    gnu
    -0.63
    Fight
    -0.63
    cher
    -0.62
    POSITIVE LOGITS
     quantities
    1.42
     amounts
    1.34
     scale
    1.29
     sums
    1.23
     numbers
    1.18
     swat
    1.13
     chunks
    1.11
    scale
    1.08
     tracts
    1.07
    pox
    1.07
    Activations Density 0.090%

    No Known Activations