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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 21466
    Prev
    Next
    INDEX
    Explanations

    court case names listed in a specific format: "vs" followed by the opposing parties

    oai_token-act-pair · gpt-3.5-turbo

    references to legal cases and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.74
    ãĥĨ
    -0.72
    bach
    -0.66
    thritis
    -0.66
    Nob
    -0.64
     downstream
    -0.61
     untreated
    -0.60
    --------------------------------------------------------
    -0.59
    emi
    -0.59
     Pioneer
    -0.59
    POSITIVE LOGITS
    arsity
    0.93
    oodoo
    0.91
    iii
    0.90
    iably
    0.85
    uv
    0.84
    ince
    0.83
    ii
    0.81
    III
    0.80
    iving
    0.79
    als
    0.78
    Activations Density 0.010%

    No Known Activations