© 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. 16042
    Prev
    Next
    INDEX
    Explanations

    terms related to numbers, financial transactions, and technical language in a document

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conditions, restrictions, or specifications in a variety of 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
    hess
    -0.73
    onomy
    -0.69
     Debor
    -0.68
    thought
    -0.68
    liest
    -0.67
    hof
    -0.65
    osity
    -0.65
    lvl
    -0.65
     Hollande
    -0.64
    veland
    -0.64
    POSITIVE LOGITS
     incidental
    1.02
    ishable
    1.02
     non
    1.02
     unauthorized
    0.91
     liquids
    0.89
     persons
    0.88
     nont
    0.88
     those
    0.87
     transient
    0.86
     hybrids
    0.86
    Activations Density 0.457%

    No Known Activations