© 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. 10-RES-JB
    11. 13824
    Prev
    Next
    INDEX
    Explanations

    specific locations or boundaries within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or jurisdictions

    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
    opal
    -0.74
    rex
    -0.70
    hire
    -0.67
    onna
    -0.67
    wives
    -0.65
    earch
    -0.65
    daq
    -0.63
    odore
    -0.62
    eday
    -0.62
    aler
    -0.61
    POSITIVE LOGITS
     confines
    1.77
     bounds
    1.47
     boundaries
    1.22
     limits
    1.17
     framework
    1.17
     context
    1.10
     scope
    1.08
     parameters
    1.06
     radius
    1.06
     borders
    1.05
    Activations Density 0.138%

    No Known Activations