© 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. 18134
    Prev
    Next
    INDEX
    Explanations

    physical attributes or spatial orientations like "vertical" or "horizontally."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to vertical alignment or orientation

    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
    giving
    -0.93
    ãģ®éŃĶ
    -0.85
    ãģ¦
    -0.85
    keeper
    -0.78
    gans
    -0.78
    mberg
    -0.76
    $$
    -0.76
    tto
    -0.75
    IVERS
    -0.73
    REDACTED
    -0.73
    POSITIVE LOGITS
     axis
    1.01
     vertical
    0.94
     earthqu
    0.93
     stripes
    0.92
     dimension
    0.91
     separation
    0.89
    izont
    0.86
     dimensions
    0.85
     horizontal
    0.85
     takeoff
    0.83
    Activations Density 0.011%

    No Known Activations