© 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. 20759
    Prev
    Next
    INDEX
    Explanations

    mentions of specific positions or roles within a team, such as "center," "linebacker," or "shooting guard."

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or positions within a context

    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
    SPONSORED
    -0.74
    thodox
    -0.70
     guiActiveUnfocused
    -0.69
    20439
    -0.68
     externalToEVAOnly
    -0.67
     Bezos
    -0.64
    udence
    -0.62
    emet
    -0.61
    quartered
    -0.61
    esome
    -0.60
    POSITIVE LOGITS
     fullback
    1.06
     halftime
    1.04
     shortstop
    0.95
     quarterback
    0.88
    onement
    0.86
     QB
    0.85
     Rookie
    0.83
     least
    0.83
    iddling
    0.82
    iba
    0.82
    Activations Density 0.121%

    No Known Activations