© 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. 0-RES-JB
    11. 16460
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bridge."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hyp
    -0.72
     subt
    -0.69
    UID
    -0.67
     pant
    -0.63
     Tit
    -0.63
     FDA
    -0.62
     OCD
    -0.62
     exclus
    -0.61
     insured
    -0.61
     accuracy
    -0.61
    POSITIVE LOGITS
    bridge
    4.83
    Bridge
    2.01
    brid
    1.68
     Bridge
    1.50
     bridge
    1.46
    bury
    1.33
    minster
    1.23
     Bridges
    1.22
    fleet
    1.11
    gate
    1.11
    Activations Density 0.013%

    No Known Activations