© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 21354
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities, particularly bridges

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, notable events, or entities associated with infrastructure and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microw
    -0.85
     allerg
    -0.82
    SAM
    -0.78
    agents
    -0.75
    Magazine
    -0.75
    eln
    -0.75
    cookie
    -0.74
    acion
    -0.74
     Santorum
    -0.73
    MAG
    -0.72
    POSITIVE LOGITS
     bridge
    2.29
     Bridge
    2.18
     bridges
    2.05
    Bridge
    1.88
     Bridges
    1.84
    bridge
    1.56
     brid
    1.45
     crossings
    1.42
     crossing
    1.38
     river
    1.33
    Activations Density 0.193%

    No Known Activations