© 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. 4389
    Prev
    Next
    INDEX
    Explanations

    company names, historical terms, medical and health-related terms, environmental terms, legal terms, and terms related to energy and technology

    oai_token-act-pair · gpt-3.5-turbo

    specific product, organization, or social policy references

    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
    ============
    -0.75
    ãĤ¦
    -0.67
    ãĤ«
    -0.66
    ========
    -0.66
    ãģĨ
    -0.66
    ãĢ
    -0.65
    ================================================================
    -0.64
    advertising
    -0.63
    ________________________________________________________________
    -0.62
    `.
    -0.61
    POSITIVE LOGITS
     itself
    0.73
     altogether
    0.70
     differently
    0.70
     elsewhere
    0.70
     separately
    0.66
     twice
    0.65
     entirely
    0.64
     firsthand
    0.63
     alongside
    0.62
     already
    0.61
    Activations Density 0.856%

    No Known Activations