© 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. 10-RES-JB
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    references to political figures, particularly those with the last name "Kennedy" and organization names abbreviations including "F" and "B" or "I"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or organizations, particularly with abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.84
    vana
    -0.72
    vae
    -0.69
    hoe
    -0.64
     guiActiveUnfocused
    -0.63
     Nadu
    -0.61
    mble
    -0.61
    hole
    -0.61
    nut
    -0.61
    wcs
    -0.61
    POSITIVE LOGITS
    ruary
    0.79
    ogle
    0.79
    existent
    0.75
     Kennedy
    0.75
    ancial
    0.69
    enhagen
    0.69
    owship
    0.67
    ortunately
    0.67
    andom
    0.66
     Proxy
    0.65
    Activations Density 0.034%

    No Known Activations