© 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. 1-RES-JB
    11. 7235
    Prev
    Next
    INDEX
    Explanations

    mentions of mergers, acquisitions, and potentially legal or business-related processes

    oai_token-act-pair · gpt-3.5-turbo

    references to mergers or related corporate activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORY
    -0.73
     Eleven
    -0.67
    YE
    -0.66
     Decay
    -0.65
    ¬¼
    -0.65
     Rasmussen
    -0.65
    BOOK
    -0.63
     fixed
    -0.63
    090
    -0.63
     Fathers
    -0.63
    POSITIVE LOGITS
    cedes
    1.12
     mer
    1.11
     simultane
    0.90
    maid
    0.89
    folk
    0.89
     satell
    0.87
     concess
    0.87
    natureconservancy
    0.86
    utenberg
    0.84
    cial
    0.83
    Activations Density 0.003%

    No Known Activations