© 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. 10-RES-JB
    11. 5420
    Prev
    Next
    INDEX
    Explanations

    names of individuals starting with "Jo"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Jo" 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
    raits
    -0.71
     IMAGES
    -0.66
     numbered
    -0.64
    practice
    -0.62
    tracks
    -0.62
     worse
    -0.62
    Reloaded
    -0.62
    BALL
    -0.61
     contrary
    -0.61
     interests
    -0.60
    POSITIVE LOGITS
    aquin
    1.43
    ining
    1.29
    anne
    1.20
    Jo
    1.20
    ppa
    1.19
    Anne
    1.16
    anna
    1.10
    aqu
    1.10
    ão
    1.10
    Ann
    1.04
    Activations Density 0.023%

    No Known Activations