© 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. 6-RES-JB
    11. 12851
    Prev
    Next
    INDEX
    Explanations

    "Fredric", a specific name

    oai_token-act-pair · gpt-3.5-turbo

    the name "Fredric" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.91
    ĸļ
    -0.75
     TJ
    -0.72
     Cosponsors
    -0.70
     Emanuel
    -0.66
     CTR
    -0.64
     Whale
    -0.64
    gression
    -0.63
    irk
    -0.62
    mberg
    -0.62
    POSITIVE LOGITS
    ycle
    1.06
    ity
    0.95
    ultural
    0.93
    ulously
    0.89
     Vaugh
    0.88
    entric
    0.88
    ulum
    0.87
    hetti
    0.84
    ulous
    0.83
    ulture
    0.80
    Activations Density 0.017%

    No Known Activations