© 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. 10-RES-JB
    11. 16123
    Prev
    Next
    INDEX
    Explanations

    instances where an action is taken or an event occurs

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .).
    -0.57
    !.
    -0.53
    !).
    -0.51
    +.
    -0.51
    .''
    -0.50
    )!
    -0.50
    %.
    -0.49
    '.
    -0.49
    $.
    -0.49
    .ãĢį
    -0.49
    POSITIVE LOGITS
    ividual
    0.60
    osponsors
    0.59
    bernatorial
    0.59
     subur
    0.55
     regarding
    0.54
     associated
    0.52
    imentary
    0.51
    pez
    0.51
    oided
    0.50
    ivalent
    0.50
    Activations Density 1.420%

    No Known Activations