© 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. 9397
    Prev
    Next
    INDEX
    Explanations

    phrases indicating chronological sequence

    oai_token-act-pair · gpt-3.5-turbo

    sequences indicating a chronological order or progression of events

    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
    Of
    -0.67
    of
    -0.65
     Of
    -0.62
    /
    -0.61
    natureconservancy
    -0.57
     OF
    -0.51
    OF
    -0.51
    Gameplay
    -0.50
    etc
    -0.50
     whats
    -0.48
    POSITIVE LOGITS
     to
    0.66
    ,—
    0.65
    yss
    0.60
     onstage
    0.58
    isively
    0.57
    forth
    0.56
    ?,
    0.55
    ,
    0.55
    ioned
    0.54
     thereto
    0.52
    Activations Density 0.778%

    No Known Activations