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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13600
    Prev
    Next
    INDEX
    Explanations

    the word "Freddie" at various positions in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Freddie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elevation
    -0.67
     scroll
    -0.66
     remote
    -0.64
     tasks
    -0.64
     leaf
    -0.64
     Pradesh
    -0.64
     lizard
    -0.63
    istani
    -0.62
     native
    -0.62
     ecosystem
    -0.62
    POSITIVE LOGITS
     Freddie
    4.29
    Fred
    1.78
     Freddy
    1.72
    annie
    1.45
     Frankie
    1.40
    Baltimore
    1.19
     Nig
    1.17
     Trayvon
    1.17
     Sonny
    1.16
     Manny
    1.11
    Activations Density 0.023%

    No Known Activations