© 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. 4-RES-JB
    11. 4815
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "MC" followed by a number (e.g., MC 10, MC 9) to specify certain entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Marvel Cinematic Universe (MCU)

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

    No Comments

    Negative Logits
    éĹĺ
    -0.80
     Gingrich
    -0.77
    ãĥ³ãĤ¸
    -0.72
     Meier
    -0.70
    ãĥ¼ãĥ
    -0.70
    ãĤ¦ãĤ¹
    -0.69
    ãĤª
    -0.67
    Ô
    -0.67
    ãĥ¼ãĥĨ
    -0.66
     misplaced
    -0.66
    POSITIVE LOGITS
    MC
    1.23
    intosh
    1.01
    GRE
    0.93
    abre
    0.87
    SA
    0.86
    ascade
    0.84
    illion
    0.83
    ONEY
    0.82
    GUI
    0.82
    Fs
    0.81
    Activations Density 0.009%

    No Known Activations