© 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. 578
    Prev
    Next
    INDEX
    Explanations

    names of companies or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to company or organization names, particularly those labeled as "Group."

    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
    lvl
    -0.75
    cale
    -0.70
    itability
    -0.68
    DAY
    -0.68
    issance
    -0.68
    DIT
    -0.68
    dri
    -0.67
    piration
    -0.67
    ANCE
    -0.67
    ynes
    -0.66
    POSITIVE LOGITS
    roups
    0.89
     Holding
    0.88
     Group
    0.85
    arettes
    0.79
     Holdings
    0.79
    emonium
    0.73
     Paper
    0.71
     LLC
    0.71
     Publishers
    0.70
     Partnership
    0.70
    Activations Density 0.016%

    No Known Activations