© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16631
    Prev
    Next
    INDEX
    Explanations

    the format of a command or instruction

    oai_token-act-pair · gpt-3.5-turbo

    themes related to societal rules and critiques of authority

    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
     caveats
    -0.60
    ortium
    -0.59
     caveat
    -0.56
     rede
    -0.53
    BuyableInstoreAndOnline
    -0.52
     unanimous
    -0.51
     peaked
    -0.50
     reiterate
    -0.50
     notable
    -0.50
     unden
    -0.49
    POSITIVE LOGITS
    .[
    0.95
    .</
    0.94
    .?
    0.92
    .",
    0.92
    .''.
    0.90
    .ãĢį
    0.89
    .
    0.88
    .''
    0.87
    .;
    0.86
    .","
    0.86
    Activations Density 0.855%

    No Known Activations