© 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. 9526
    Prev
    Next
    INDEX
    Explanations

    names and specific terms related to people, such as "John" or "Simone Johnson"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Kahn" and its variations

    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
    âĹ¼
    -0.89
    accompan
    -0.81
    DragonMagazine
    -0.73
     indo
    -0.73
     bearer
    -0.71
    BuyableInstoreAndOnline
    -0.69
    EStreamFrame
    -0.66
     Founding
    -0.65
     Tempest
    -0.65
    multipl
    -0.64
    POSITIVE LOGITS
    hn
    1.26
    agar
    1.19
    eman
    1.07
    quist
    0.92
    hak
    0.89
    endon
    0.88
    emen
    0.86
    orr
    0.85
    avy
    0.85
    hardt
    0.85
    Activations Density 0.007%

    No Known Activations