© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6924
    Prev
    Next
    INDEX
    Explanations

    words related to business or ownership, particularly referring to the concept of a franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to franchises in various contexts

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

    No Comments

    Negative Logits
    board
    -0.88
    boards
    -0.77
     Trance
    -0.77
    ynthesis
    -0.74
    inx
    -0.72
    Org
    -0.71
    ools
    -0.65
    ibrary
    -0.63
    lap
    -0.62
    legraph
    -0.61
    POSITIVE LOGITS
     franchise
    0.78
    eers
    0.76
     franchises
    0.74
    rats
    0.74
    operated
    0.71
    ovies
    0.71
    atical
    0.70
     owner
    0.69
    arily
    0.68
    arium
    0.67
    Activations Density 0.016%

    No Known Activations