© 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. 4-RES-JB
    11. 20911
    Prev
    Next
    INDEX
    Explanations

    the name "Grayson" in a political context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific politicians, particularly Grayson and Tusk

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

    No Comments

    Negative Logits
     Tribune
    -0.78
    olog
    -0.75
    bara
    -0.74
    Japan
    -0.74
    thia
    -0.70
    este
    -0.69
    rums
    -0.69
    veh
    -0.68
    emet
    -0.68
    plates
    -0.68
    POSITIVE LOGITS
    ibility
    0.68
    efully
    0.65
     Drake
    0.63
    ible
    0.62
    fly
    0.62
     Indigo
    0.60
     Gaga
    0.60
    schild
    0.59
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.59
     Eag
    0.59
    Activations Density 0.031%

    No Known Activations