© 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. 9-RES-JB
    11. 15844
    Prev
    Next
    INDEX
    Explanations

    people's ages

    oai_token-act-pair · gpt-3.5-turbo

    references to the ages of 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
    ascript
    -1.00
    mbuds
    -0.99
    Ô
    -0.97
    hovah
    -0.93
    ecause
    -0.88
    illance
    -0.86
    irtual
    -0.84
    ravings
    -0.83
    qqa
    -0.83
    thia
    -0.82
    POSITIVE LOGITS
     Frenchman
    1.10
     lawmaker
    0.98
     duo
    0.97
     politician
    0.97
     singer
    0.95
     businessman
    0.92
     artist
    0.91
     senator
    0.90
     musician
    0.89
     rapper
    0.89
    Activations Density 0.078%

    No Known Activations