© 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. 4-RES-JB
    11. 7506
    Prev
    Next
    INDEX
    Explanations

    terms related to ownership or legal control

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or ownership rights

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

    No Comments

    Negative Logits
    olson
    -0.68
     Arrows
    -0.64
    uated
    -0.63
    oward
    -0.63
     threaded
    -0.62
    tiny
    -0.62
     Christensen
    -0.62
    arette
    -0.61
     Clover
    -0.60
     stride
    -0.60
    POSITIVE LOGITS
     rights
    1.05
    rights
    0.88
    holder
    0.86
     infringement
    0.84
     Rights
    0.82
    ignty
    0.81
    ktop
    0.80
     holders
    0.78
     holder
    0.78
     expired
    0.76
    Activations Density 0.021%

    No Known Activations