© 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. 13280
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person named "Ric" followed by either accolades or physical attributes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ric" and various types of "braces."

    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
    Dun
    -0.70
    zu
    -0.69
     Ezek
    -0.68
    ername
    -0.68
    pg
    -0.66
    GMT
    -0.65
     CHO
    -0.65
     Wolfe
    -0.65
     dd
    -0.64
    wang
    -0.64
    POSITIVE LOGITS
     Ric
    3.13
     brace
    1.82
     ric
    1.48
     Laf
    1.10
     Gir
    0.98
     Arn
    0.97
     braces
    0.97
     Acad
    0.89
     Sic
    0.87
     Grav
    0.83
    Activations Density 0.019%

    No Known Activations