© 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. 9-RES-JB
    11. 4671
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive attributes or qualities like well-regarded, well-deserved, and well-resourced

    oai_token-act-pair · gpt-3.5-turbo

    words related to regulation and governance

    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
    knife
    -0.68
    mania
    -0.63
    agents
    -0.62
    pora
    -0.61
     Decoder
    -0.60
    magic
    -0.60
    Discussion
    -0.60
    wolves
    -0.60
     Jackets
    -0.60
    terms
    -0.58
    POSITIVE LOGITS
    ented
    1.09
    ited
    1.07
    ivated
    1.06
    oured
    1.02
    ated
    1.02
    enged
    1.02
    arded
    1.01
    ested
    1.00
    ioned
    1.00
    ured
    0.98
    Activations Density 0.172%

    No Known Activations