© 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. 11-RES-JB
    11. 615
    Prev
    Next
    INDEX
    Explanations

    quantitative information related to estimates and averages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "an" in various contexts related to statistics and estimates

    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
    verting
    -0.77
     Punk
    -0.66
    selves
    -0.65
     Shelter
    -0.61
    BAT
    -0.60
    mson
    -0.60
     Writ
    -0.57
     Paste
    -0.56
    gui
    -0.56
    ware
    -0.54
    POSITIVE LOGITS
     astounding
    1.14
     average
    1.10
     astonishing
    1.07
     estimated
    1.05
     additional
    1.00
     impressive
    0.99
     incredible
    0.98
     awful
    0.96
     enormous
    0.95
     hour
    0.93
    Activations Density 0.119%

    No Known Activations