© 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. 11-RES-JB
    11. 14946
    Prev
    Next
    INDEX
    Explanations

    phrases related to external interference or intervention

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government interference and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.80
     Gleaming
    -0.71
    \\\\\\\\
    -0.66
     Warp
    -0.63
     Diesel
    -0.63
    ãĥ¥
    -0.62
    iku
    -0.62
     Bender
    -0.62
    furt
    -0.59
     Passage
    -0.59
    POSITIVE LOGITS
     into
    0.93
     milit
    0.82
    ially
    0.78
    ifles
    0.74
    ateral
    0.73
     in
    0.73
    ist
    0.71
    ism
    0.70
     intervene
    0.70
    judicial
    0.69
    Activations Density 0.058%

    No Known Activations