© 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. 6-RES-JB
    11. 7780
    Prev
    Next
    INDEX
    Explanations

    phrases related to public figures and their actions, particularly in a political context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to claims and statements made by individuals, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agar
    -0.79
    td
    -0.70
    allery
    -0.69
    udic
    -0.68
    ason
    -0.67
    arist
    -0.66
    neau
    -0.66
    ept
    -0.66
    central
    -0.65
     Brill
    -0.65
    POSITIVE LOGITS
     himself
    0.85
     surrog
    0.84
     lewd
    0.80
     retweet
    0.77
     tweeting
    0.75
     Tonight
    0.74
    gyn
    0.73
     onstage
    0.73
     sarcast
    0.72
     insults
    0.71
    Activations Density 0.478%

    No Known Activations