© 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. 1-RES-JB
    11. 3814
    Prev
    Next
    INDEX
    Explanations

    references to people with the prefix "Mc" followed by a strong positive sentiment or action

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Mc"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.72
     Uriel
    -0.71
    DragonMagazine
    -0.68
     Gemini
    -0.67
     Alexis
    -0.66
     unprotected
    -0.66
    inates
    -0.66
    */(
    -0.66
    ãĤ¯
    -0.64
     ACS
    -0.63
    POSITIVE LOGITS
    intosh
    1.27
    Afee
    1.21
    donald
    1.08
    Leod
    0.96
    agar
    0.88
    Connell
    0.88
    Lean
    0.88
    hesda
    0.88
    Donnell
    0.86
    haw
    0.85
    Activations Density 0.005%

    No Known Activations