© 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. 24004
    Prev
    Next
    INDEX
    Explanations

    quantitative or comparative adjectives indicating size or amount

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or proportions

    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
    cair
    -0.81
    iddles
    -0.75
    inances
    -0.75
    atography
    -0.74
    Mania
    -0.70
    agate
    -0.70
     carts
    -0.69
    adobe
    -0.69
    ptives
    -0.69
    events
    -0.69
    POSITIVE LOGITS
     proportion
    1.62
     percentage
    1.57
     portion
    1.54
     swath
    1.41
     chunk
    1.40
     fraction
    1.38
     number
    1.37
     share
    1.26
     majority
    1.25
     minority
    1.24
    Activations Density 0.113%

    No Known Activations