© 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. 20863
    Prev
    Next
    INDEX
    Explanations

    references to the Republican strategist Karl Rove

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, particularly Karl Rove

    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
    Constructed
    -0.81
     Mehran
    -0.69
    ELF
    -0.68
    WARE
    -0.67
    hops
    -0.66
    malink
    -0.65
    board
    -0.65
     Qiao
    -0.63
    ++++++++
    -0.62
     Examiner
    -0.62
    POSITIVE LOGITS
     Rove
    0.99
    wolves
    0.83
    hardt
    0.80
    rils
    0.80
    reens
    0.78
    olf
    0.76
    encer
    0.74
    cot
    0.74
    ril
    0.74
    ttes
    0.74
    Activations Density 0.023%

    No Known Activations