© 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. 17051
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal activities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of biking or walking activities

    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
     destro
    -0.60
    rule
    -0.59
    =[
    -0.57
    =>
    -0.57
    archy
    -0.55
     Detected
    -0.55
    peat
    -0.54
    yle
    -0.54
     abound
    -0.54
     BELOW
    -0.54
    POSITIVE LOGITS
     when
    1.68
    when
    1.58
     WHEN
    1.19
    When
    0.90
     When
    0.89
     shortly
    0.86
     whenever
    0.85
    livious
    0.75
     heading
    0.71
     asleep
    0.70
    Activations Density 0.475%

    No Known Activations