© 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. 1-RES-JB
    11. 20012
    Prev
    Next
    INDEX
    Explanations

    terms related to the presence of potentially harmful or disease-causing substances or components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substances or processes that are harmful or induce chemical reactions

    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
    dimension
    -0.75
    stood
    -0.73
     subcontract
    -0.64
    suff
    -0.64
    rows
    -0.62
     paramed
    -0.61
    Contract
    -0.60
     appra
    -0.59
     Dillon
    -0.59
     Kinnikuman
    -0.58
    POSITIVE LOGITS
    ogenic
    1.38
    ogens
    0.98
    otine
    0.82
    atory
    0.75
    emic
    0.71
    itational
    0.70
    ãĥ³ãĤ¸
    0.69
    lihood
    0.68
     Flavoring
    0.66
    etically
    0.66
    Activations Density 0.013%

    No Known Activations