© 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. 5801
    Prev
    Next
    INDEX
    Explanations

    specific capitalized words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "don" and related terms or identifiers in the text

    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
    ord
    -0.75
    ia
    -0.71
    hai
    -0.71
    user
    -0.70
    opol
    -0.69
    us
    -0.68
    ibel
    -0.68
    je
    -0.68
    adem
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.64
    POSITIVE LOGITS
    WAYS
    1.43
    BRE
    1.36
    ISM
    1.35
    FORM
    1.35
    ABLE
    1.34
    MAN
    1.33
    COL
    1.32
    ER
    1.32
    LINE
    1.31
    VER
    1.30
    Activations Density 0.127%

    No Known Activations