© 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. 3-RES-JB
    11. 1744
    Prev
    Next
    INDEX
    Explanations

    words related to mergers, acquisitions, and specific company names

    oai_token-act-pair · gpt-3.5-turbo

    references to mergers or combinations involving entities or items

    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
    ONES
    -0.78
    ¬¼
    -0.75
     Shelter
    -0.70
     fixed
    -0.66
    ORY
    -0.66
     Pal
    -0.66
    URN
    -0.65
    ORN
    -0.64
     Poverty
    -0.62
    HAEL
    -0.62
    POSITIVE LOGITS
    cedes
    1.26
    maid
    1.04
    folk
    0.94
    idian
    0.93
    cial
    0.92
    iously
    0.92
    ited
    0.90
    gency
    0.86
    rily
    0.84
    gers
    0.84
    Activations Density 0.003%

    No Known Activations