© 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. 0-RES-JB
    11. 12610
    Prev
    Next
    INDEX
    Explanations

    terms related to the abbreviation "POS" or "position"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Pos" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andal
    -0.78
     crystal
    -0.73
     regeneration
    -0.73
    mble
    -0.69
     Abbey
    -0.69
     Collector
    -0.68
     DRM
    -0.67
     gorge
    -0.67
    emaker
    -0.67
     storm
    -0.67
    POSITIVE LOGITS
     Pos
    3.84
    Pos
    2.51
     Position
    2.32
    Position
    1.96
     POS
    1.95
    POS
    1.70
     positions
    1.55
     position
    1.33
     positional
    1.31
    pos
    1.31
    Activations Density 0.020%

    No Known Activations