© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    specific dates or events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant dates and events, particularly related to elections and holidays

    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
    hesive
    -0.74
    glomer
    -0.68
     handle
    -0.65
    osphere
    -0.64
     environment
    -0.61
    aser
    -0.60
     accompanying
    -0.59
    uggish
    -0.58
     constitu
    -0.58
     executable
    -0.57
    POSITIVE LOGITS
     Day
    1.93
     day
    1.58
    Day
    1.54
     DAY
    1.50
     Month
    1.46
     Week
    1.45
    uesday
    1.44
    day
    1.44
    days
    1.42
    nesday
    1.41
    Activations Density 0.312%

    No Known Activations