© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10665
    Prev
    Next
    INDEX
    Explanations

    the name "Fredric" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Fredric."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.76
     Jem
    -0.73
    £ı
    -0.71
     TJ
    -0.71
     WS
    -0.67
    ĸļ
    -0.66
     Colt
    -0.65
    */(
    -0.62
     largeDownload
    -0.62
     Reese
    -0.61
    POSITIVE LOGITS
    ycle
    1.04
     Vaugh
    0.95
    hess
    0.91
    entric
    0.86
    rics
    0.86
    ity
    0.85
    ulum
    0.82
    ultural
    0.80
    ric
    0.80
    ulously
    0.78
    Activations Density 0.012%

    No Known Activations