© 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. 8-RES-JB
    11. 3849
    Prev
    Next
    INDEX
    Explanations

    words related to names of people and places, such as "Vallejo," "Portugal," and "Gordão."

    oai_token-act-pair · gpt-3.5-turbo

    words or syllables with the letters "le" or "re."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iversal
    -0.62
     pickup
    -0.58
     accelerator
    -0.58
    umbn
    -0.55
     SEM
    -0.54
     yarn
    -0.54
     desks
    -0.52
     experiment
    -0.51
     SHARES
    -0.51
     microscope
    -0.51
    POSITIVE LOGITS
    cci
    1.00
    zza
    0.94
    zzo
    0.91
    ña
    0.89
    jo
    0.89
    agles
    0.88
    gan
    0.88
    ño
    0.87
    cca
    0.87
    ggy
    0.80
    Activations Density 0.120%

    No Known Activations