© 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. 20569
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or persons

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Al" in various contexts

    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
     disappearing
    -0.67
     membership
    -0.64
    ãģ¯
    -0.63
     operating
    -0.62
     underwater
    -0.62
     transporting
    -0.61
     amounts
    -0.60
     soaring
    -0.60
     surging
    -0.59
     opaque
    -0.59
    POSITIVE LOGITS
    mberg
    0.96
    antz
    0.93
    ickson
    0.92
    bath
    0.91
    bre
    0.91
    bery
    0.90
    stadt
    0.88
    verson
    0.86
    jac
    0.85
    zman
    0.85
    Activations Density 0.122%

    No Known Activations