© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18704
    Prev
    Next
    INDEX
    Explanations

    mentions of equipment or tools

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate items or entities that are provided with certain features or capabilities

    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
     Flavoring
    -0.66
     Causes
    -0.63
    amin
    -0.63
    rase
    -0.63
    asta
    -0.62
    birth
    -0.62
     Decay
    -0.61
    clamation
    -0.60
    cott
    -0.58
     Mub
    -0.58
    POSITIVE LOGITS
    fitted
    0.82
    ments
    0.81
    oise
    0.79
     equipped
    0.78
    bodied
    0.74
    itted
    0.73
     bod
    0.72
    equipped
    0.72
    iterranean
    0.69
     shelves
    0.68
    Activations Density 0.067%

    No Known Activations