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

    Neuronpedia

    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. 18445
    Prev
    Next
    INDEX
    Explanations

    references to the stock of items or products

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stock."

    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
    mes
    -0.81
    BLE
    -0.81
    inx
    -0.77
    undai
    -0.75
    ptoms
    -0.75
    soever
    -0.74
    theless
    -0.71
    mentation
    -0.68
    partisan
    -0.66
    pty
    -0.65
    POSITIVE LOGITS
    holders
    1.12
    holder
    0.91
    holm
    0.84
    yards
    0.79
    ings
    0.73
    seed
    0.69
    still
    0.67
    taking
    0.67
    ivities
    0.67
     footage
    0.66
    Activations Density 0.008%

    No Known Activations