© 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. 8-RES-JB
    11. 11069
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals or businesses

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the substring "ks" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENTS
    -0.80
     Jinn
    -0.66
    ments
    -0.62
     Galile
    -0.62
     forfeiture
    -0.60
    MENT
    -0.59
    zzi
    -0.58
     Abbas
    -0.58
     citation
    -0.58
    ollah
    -0.56
    POSITIVE LOGITS
    ystem
    1.48
    creen
    1.43
    paces
    1.37
    pace
    1.34
    hip
    1.29
    cape
    1.28
    erver
    1.27
    pread
    1.27
    ilver
    1.26
    erker
    1.25
    Activations Density 0.146%

    No Known Activations