© 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. 6381
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mous sa" with different activations for variations of the name

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly with the name "Moussa."

    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
    LIN
    -0.84
    starter
    -0.81
     unaff
    -0.76
    breaks
    -0.72
    tails
    -0.71
    ships
    -0.68
     Chrom
    -0.66
    erous
    -0.65
     Cavaliers
    -0.65
    line
    -0.65
    POSITIVE LOGITS
    pling
    1.37
    plings
    1.15
    fters
    1.01
    uthor
    1.00
    isoft
    0.98
    velength
    0.98
    ption
    0.96
    uton
    0.96
    uble
    0.95
    terday
    0.92
    Activations Density 0.010%

    No Known Activations