© 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. 3-RES-JB
    11. 5873
    Prev
    Next
    INDEX
    Explanations

    references to specific astronomical objects and historical figures in astronomy

    oai_token-act-pair · gpt-3.5-turbo

    references to notable astronomers and their discoveries

    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
    rha
    -0.86
    alg
    -0.82
    ashtra
    -0.81
    atche
    -0.77
    cgi
    -0.75
    uro
    -0.75
    ions
    -0.74
    thia
    -0.74
    Western
    -0.74
    cs
    -0.74
    POSITIVE LOGITS
     Kepler
    0.90
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.85
     Maxwell
    0.70
    âĶĢâĶĢâĶĢâĶĢ
    0.68
     Morales
    0.67
     Inquisition
    0.64
    naissance
    0.61
     Pref
    0.60
     Holmes
    0.60
     Barker
    0.60
    Activations Density 0.008%

    No Known Activations