© 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. 8-RES-JB
    11. 1074
    Prev
    Next
    INDEX
    Explanations

    proper nouns ending with "Jr"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the title "Jr." related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comprom
    -0.63
     festive
    -0.63
     shards
    -0.62
    keeping
    -0.61
     revolving
    -0.60
    theless
    -0.59
     Ninth
    -0.58
     frontier
    -0.57
    =-=-=-=-=-=-=-=-
    -0.57
    void
    -0.57
    POSITIVE LOGITS
    .,
    1.46
    arcer
    1.13
    .;
    1.11
    .?
    1.11
    .,"
    1.04
    .:
    1.03
    ./
    1.03
    .—
    0.97
    orporated
    0.96
    onse
    0.96
    Activations Density 0.020%

    No Known Activations