© 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. 2-RES-JB
    11. 22408
    Prev
    Next
    INDEX
    Explanations

    the word "lawmakers"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of lawmakers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.87
    thritis
    -0.75
    --+
    -0.74
     Carbuncle
    -0.72
    co
    -0.69
     Infinite
    -0.67
     Goat
    -0.66
     Satanic
    -0.66
    OUS
    -0.63
     Absolute
    -0.63
    POSITIVE LOGITS
    woman
    0.92
    interstitial
    0.91
     lawmakers
    0.88
     lawmaker
    0.83
    ongyang
    0.82
    ratulations
    0.81
    hips
    0.81
    arians
    0.81
     legislators
    0.80
    rences
    0.79
    Activations Density 0.017%

    No Known Activations