© 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. 3-RES-JB
    11. 622
    Prev
    Next
    INDEX
    Explanations

    words related to auctions and bidding

    oai_token-act-pair · gpt-3.5-turbo

    words related to bidding and contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.74
    OGR
    -0.69
    OTE
    -0.69
    aro
    -0.68
    issance
    -0.67
     antioxid
    -0.66
    atile
    -0.66
    OUP
    -0.65
    het
    -0.65
    arde
    -0.63
    POSITIVE LOGITS
    bid
    1.17
    few
    0.78
    theless
    0.72
     EDITION
    0.72
    fold
    0.71
    irection
    0.71
    liest
    0.70
    fy
    0.69
    mand
    0.68
    ties
    0.68
    Activations Density 0.044%

    No Known Activations