© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6880
    Prev
    Next
    INDEX
    Explanations

    specific individuals or roles in a professional or political context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubb
    -0.74
    ashtra
    -0.67
    LESS
    -0.64
    lio
    -0.64
    ople
    -0.64
    jee
    -0.63
    ieval
    -0.63
    "}],"
    -0.62
    oes
    -0.62
    eor
    -0.61
    POSITIVE LOGITS
     well
    1.01
     opposed
    0.98
    part
    0.83
     collateral
    0.83
    pires
    0.82
     soon
    0.80
     inspiration
    0.80
     follows
    0.80
     proof
    0.79
     part
    0.79
    Activations Density 0.127%

    No Known Activations