© 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. 4-RES-JB
    11. 20719
    Prev
    Next
    INDEX
    Explanations

    the name "Ghomihi" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "hi."

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

    No Comments

    Negative Logits
    lain
    -0.72
    swick
    -0.71
    NetMessage
    -0.71
    nesday
    -0.69
     Aven
    -0.69
     Cosponsors
    -0.68
    imentary
    -0.68
    argon
    -0.67
    ividual
    -0.67
     convol
    -0.66
    POSITIVE LOGITS
    emi
    1.02
    ya
    1.01
    pper
    0.94
    wa
    0.92
    qq
    0.88
    veland
    0.87
    ELD
    0.86
    yy
    0.85
    pping
    0.84
    pless
    0.84
    Activations Density 0.007%

    No Known Activations