© 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. 3-RES-JB
    11. 531
    Prev
    Next
    INDEX
    Explanations

    names of notable personalities, such as "DeVos" and "Dawkins."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Betsy DeVos and Richard Dawkins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polic
    -0.79
     Fant
    -0.78
     Leth
    -0.71
     Pike
    -0.70
     pneum
    -0.68
     Lith
    -0.66
     buoy
    -0.65
     Antar
    -0.64
     fishermen
    -0.64
    ppo
    -0.62
    POSITIVE LOGITS
    liga
    0.90
    æł
    0.86
    etics
    0.84
    à¼
    0.84
    heimer
    0.83
    chool
    0.81
    ãĥ¼ãĥĨãĤ£
    0.80
    ulously
    0.79
    verse
    0.76
    hyde
    0.75
    Activations Density 0.021%

    No Known Activations