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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15467
    Prev
    Next
    INDEX
    Explanations

    numerical results or findings

    oai_token-act-pair · gpt-3.5-turbo

    references to research findings or outcomes

    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
    neau
    -0.63
     vigil
    -0.62
     leisure
    -0.62
     capital
    -0.62
    cer
    -0.62
    capital
    -0.62
    ACP
    -0.61
    pload
    -0.60
     hopping
    -0.60
    oos
    -0.60
    POSITIVE LOGITS
    results
    0.89
     results
    0.88
    Results
    0.80
    iments
    0.78
     Results
    0.74
     thereof
    0.73
    orge
    0.73
     result
    0.71
    iveness
    0.71
    ource
    0.71
    Activations Density 0.021%

    No Known Activations