© 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. 9-RES-JB
    11. 7297
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific political figures such as Lindsey Graham and Marco Rubio

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures, particularly related to Lindsey Graham and Marco Rubio

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iop
    -0.80
    icator
    -0.74
    quartered
    -0.73
    igmatic
    -0.72
    hops
    -0.70
    knife
    -0.69
    WithNo
    -0.69
    icating
    -0.69
    士
    -0.65
    elf
    -0.65
    POSITIVE LOGITS
     Rubio
    0.75
     Giuliani
    0.75
    xtap
    0.75
     Gingrich
    0.72
     Rubin
    0.71
    idia
    0.68
     Hendricks
    0.66
     calculus
    0.65
    ument
    0.64
    etsk
    0.63
    Activations Density 0.098%

    No Known Activations