© 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. 8-RES-JB
    11. 4092
    Prev
    Next
    INDEX
    Explanations

    instances where a specific type of action or quality is required or imposed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "these"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achus
    -0.87
    osate
    -0.79
    terness
    -0.75
    onis
    -0.73
    ppe
    -0.69
    erate
    -0.69
    ossier
    -0.68
    let
    -0.67
    cation
    -0.67
    igation
    -0.65
    POSITIVE LOGITS
     kinds
    1.23
     sorts
    1.22
     types
    1.01
     shores
    0.96
     proceedings
    0.94
     facts
    0.88
     developments
    0.86
    types
    0.85
     establishments
    0.84
     truths
    0.84
    Activations Density 0.116%

    No Known Activations