© 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. 2-RES-JB
    11. 24210
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly "Chapel."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and characters associated with chapels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disclaimer
    -0.78
     antitrust
    -0.72
     olig
    -0.68
     buck
    -0.67
    ski
    -0.65
     leash
    -0.65
     blurred
    -0.63
     dog
    -0.62
     guarant
    -0.62
     Uz
    -0.61
    POSITIVE LOGITS
     Chapel
    1.23
    rons
    0.96
    auld
    0.93
    olate
    0.93
    ilon
    0.92
    erva
    0.89
    eteria
    0.87
    cule
    0.86
    house
    0.82
    thur
    0.79
    Activations Density 0.024%

    No Known Activations