© 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. 7316
    Prev
    Next
    INDEX
    Explanations

    time-stamped data and technical information

    oai_token-act-pair · gpt-3.5-turbo

    specific time stamps or identifiers related to events

    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
    thirds
    -0.68
     warranties
    -0.67
     bloodstream
    -0.67
    hire
    -0.66
    ãĤ¹ãĥĪ
    -0.64
     Commonwealth
    -0.64
     gain
    -0.61
     halls
    -0.61
     guarantees
    -0.59
    ãĥ¼ãĥĨ
    -0.59
    POSITIVE LOGITS
    orah
    0.92
    CB
    0.83
    Favorite
    0.73
    307
    0.71
    335
    0.69
    Ability
    0.68
    ecd
    0.68
    778
    0.67
    374
    0.67
    446
    0.67
    Activations Density 0.073%

    No Known Activations