© 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. 9-RES-JB
    11. 7272
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals with the prefix "Sh"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the name "Sh" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.76
     numbered
    -0.75
     Ajax
    -0.69
     Leth
    -0.68
     Diabetes
    -0.65
     Boko
    -0.65
     coupled
    -0.63
     polio
    -0.62
     Lans
    -0.62
     Corrections
    -0.61
    POSITIVE LOGITS
    rapnel
    1.27
    ifting
    1.24
    apeshifter
    1.23
    akedown
    1.22
    aping
    1.17
    attering
    1.16
    irts
    1.16
    ackle
    1.15
    apes
    1.13
    uler
    1.12
    Activations Density 0.020%

    No Known Activations