© 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. 3-RES-JB
    11. 15233
    Prev
    Next
    INDEX
    Explanations

    references to the Notre Dame Cathedral

    oai_token-act-pair · gpt-3.5-turbo

    references to the Notre Dame Cathedral and its notable aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.80
    */(
    -0.73
    ulators
    -0.69
     stroke
    -0.69
    stroke
    -0.68
    olitan
    -0.66
    oted
    -0.65
    dyl
    -0.65
    chenko
    -0.65
    prototype
    -0.65
    POSITIVE LOGITS
     Dame
    1.49
     Notre
    0.92
    heastern
    0.92
     mosqu
    0.77
    essor
    0.76
     adolesc
    0.73
    viation
    0.70
    ANCE
    0.69
     Haram
    0.68
    cipl
    0.68
    Activations Density 0.005%

    No Known Activations