Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14629
    Prev
    Next
    INDEX
    Explanations

    references to the Founding Fathers of the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the Founding Fathers and aspects of American founding documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aspx
    -0.77
    JP
    -0.75
    andra
    -0.75
    CVE
    -0.75
    ebin
    -0.71
    tle
    -0.70
    Ru
    -0.70
    activate
    -0.69
    spin
    -0.69
    aser
    -0.69
    POSITIVE LOGITS
     Era
    1.09
     colonists
    0.99
     era
    0.93
     Fathers
    0.86
     Roosevelt
    0.85
     settlers
    0.83
     fathers
    0.81
     eras
    0.81
     thinkers
    0.80
     envisioned
    0.79
    Activations Density 0.274%

    No Known Activations