© 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. 11385
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly those with "Moh" or "Ramirez"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated reference to the name "Mohammed."

    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
    istics
    -0.98
    istically
    -0.95
    istical
    -0.75
     balloons
    -0.71
     Stra
    -0.66
     laps
    -0.65
    istic
    -0.65
    ãĥ¯
    -0.65
    ificial
    -0.65
     charms
    -0.63
    POSITIVE LOGITS
    awk
    1.47
    awks
    1.38
    sin
    1.03
    doms
    1.02
    ammad
    0.97
    atche
    0.97
    ammed
    0.92
    renheit
    0.92
    abit
    0.90
    ira
    0.88
    Activations Density 0.038%

    No Known Activations