© 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. 7-RES-JB
    11. 12693
    Prev
    Next
    INDEX
    Explanations

    names (particularly with repeated 'ula' pattern)

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Ursula" or "Pul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rings
    -0.79
    ãĤ¤ãĥĪ
    -0.73
    ificial
    -0.68
    rs
    -0.66
    angered
    -0.63
    forth
    -0.63
    rien
    -0.62
    riot
    -0.61
    pocket
    -0.61
    rd
    -0.60
    POSITIVE LOGITS
    monary
    1.01
    atile
    0.82
    oaded
    0.81
    anus
    0.79
    uted
    0.77
    cture
    0.76
    restling
    0.76
    atility
    0.74
    iple
    0.73
    ogy
    0.72
    Activations Density 0.061%

    No Known Activations