© 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. 0-RES-JB
    11. 8392
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official documents and procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.56
    ividual
    -0.56
    bage
    -0.49
    agar
    -0.49
    Synopsis
    -0.49
    room
    -0.48
    cffffcc
    -0.48
    iard
    -0.47
    ãģ«
    -0.46
    sburg
    -0.46
    POSITIVE LOGITS
     the
    1.23
     their
    0.87
     those
    0.81
     its
    0.79
     our
    0.79
     a
    0.75
    the
    0.75
     an
    0.72
     another
    0.71
     your
    0.69
    Activations Density 1.406%

    No Known Activations