© 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. 10268
    Prev
    Next
    INDEX
    Explanations

    hyphenated terms indicating a time-related concept or action

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related concepts and metrics

    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
     Cosponsors
    -0.76
     Flavoring
    -0.73
     Voice
    -0.67
     Poe
    -0.64
     EntityItem
    -0.63
     Alb
    -0.62
     Seg
    -0.61
    enza
    -0.61
     Fla
    -0.60
     xp
    -0.60
    POSITIVE LOGITS
    consuming
    1.49
    hon
    1.39
    travel
    1.33
    tested
    1.28
    saving
    1.17
    sensitive
    1.16
    delay
    1.15
    trial
    1.13
    limit
    1.11
    share
    1.10
    Activations Density 0.044%

    No Known Activations