© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4303
    Prev
    Next
    INDEX
    Explanations

    mentions of "Special Counsel" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to special operations and affiliated terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    yard
    -0.68
    atsu
    -0.67
    hari
    -0.65
    omer
    -0.63
    wp
    -0.61
    heimer
    -0.61
    bane
    -0.61
    GGGG
    -0.59
    ãĥĨãĤ£
    -0.59
    ahime
    -0.59
    POSITIVE LOGITS
     envoy
    0.95
    ties
    0.94
     Olympics
    0.92
    ised
    0.87
     prosecutor
    0.85
     Forces
    0.84
     Rapp
    0.82
    izations
    0.81
    ized
    0.81
     Operations
    0.80
    Activations Density 0.023%

    No Known Activations