© 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 EvalsExportsinterp-engineNEWAPI 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. 9201
    Prev
    Next
    INDEX
    Explanations

    entities related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    nouns or entities related to familial and social relationships

    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
    natureconservancy
    -0.61
    OME
    -0.60
    iple
    -0.59
    ¬¼
    -0.56
    :(
    -0.55
    onym
    -0.55
    resa
    -0.53
    izen
    -0.51
    odes
    -0.51
    orn
    -0.50
    POSITIVE LOGITS
     albeit
    1.04
     etc
    1.00
     respectively
    0.99
     although
    0.87
     namely
    0.82
     alas
    0.82
     whereas
    0.79
     aka
    0.78
     preferably
    0.74
     lest
    0.71
    Activations Density 1.603%

    No Known Activations