© 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. 3-RES-JB
    11. 14634
    Prev
    Next
    INDEX
    Explanations

    Japanese names and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and titles, particularly those related to individuals and cultural works

    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
    rooms
    -0.87
    sheets
    -0.85
    sheet
    -0.77
    spring
    -0.76
    mary
    -0.74
    bearing
    -0.70
    beat
    -0.69
    photos
    -0.68
    ocratic
    -0.67
    mother
    -0.67
    POSITIVE LOGITS
    oji
    0.86
    Å¡
    0.86
    ya
    0.86
    Äĩ
    0.84
    zbek
    0.84
    ÄŁ
    0.84
    pload
    0.84
    irit
    0.83
     nomine
    0.82
    atu
    0.82
    Activations Density 0.006%

    No Known Activations