© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11235
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly related to political figures, organizations, and dates

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and numerical data related to events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    opian
    -0.82
    ipl
    -0.79
    centered
    -0.75
    lig
    -0.75
    responsible
    -0.73
    capacity
    -0.73
    ves
    -0.72
    quart
    -0.72
    facing
    -0.72
    ded
    -0.71
    POSITIVE LOGITS
     Though
    1.18
     Quote
    1.17
     Although
    1.15
     While
    1.15
     Another
    1.14
     Speaking
    1.14
     Suppose
    1.11
     There
    1.11
     Despite
    1.10
     Originally
    1.08
    Activations Density 0.316%

    No Known Activations