© 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
    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. 17497
    Prev
    Next
    INDEX
    Explanations

    proper names in the format of an initial followed by a period and a last name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific player names and their statistics in sports contexts

    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
    taboola
    -0.81
    Disclaimer
    -0.79
    notations
    -0.73
    prise
    -0.73
    CVE
    -0.71
    lia
    -0.70
    ctuary
    -0.68
    SOURCE
    -0.66
    ãĥ«
    -0.66
    izoph
    -0.66
    POSITIVE LOGITS
     Phelps
    0.83
     Kear
    0.82
     Johnston
    0.82
     Berger
    0.80
     Rowling
    0.79
     Reynolds
    0.79
     Johnson
    0.78
     Bach
    0.78
     Blaz
    0.78
     Ballard
    0.78
    Activations Density 0.043%

    No Known Activations