© 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. 10238
    Prev
    Next
    INDEX
    Explanations

    references to questions and opinions being asked

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fear and uncertainty in a geopolitical context

    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
    .ãĢį
    -0.93
    .�
    -0.89
    .","
    -0.87
    !.
    -0.81
    !).
    -0.78
    +.
    -0.77
    .'"
    -0.76
     remarkably
    -0.74
    !'
    -0.74
    .'
    -0.73
    POSITIVE LOGITS
     anymore
    0.80
     his
    0.79
     criticism
    0.71
     protesters
    0.68
     divisive
    0.66
     Trump
    0.66
     negativity
    0.65
    uding
    0.65
     ousted
    0.64
     Kaepernick
    0.64
    Activations Density 0.763%

    No Known Activations