© 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. 10-RES-JB
    11. 3279
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or responsibility

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oward
    -0.77
    weet
    -0.75
    burgh
    -0.65
    Wow
    -0.65
    ru
    -0.65
    onica
    -0.63
    ews
    -0.62
    ins
    -0.62
    ileaks
    -0.62
    Suddenly
    -0.61
    POSITIVE LOGITS
     therefore
    1.39
     hence
    1.30
     cannot
    1.23
     excludes
    1.18
     thus
    1.17
     includes
    1.16
     consequently
    1.11
     should
    1.11
     may
    1.09
     requires
    1.09
    Activations Density 0.266%

    No Known Activations