© 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. 4-RES-JB
    11. 16574
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations containing "OM"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "OM" or related terms in various contexts

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

    No Comments

    Negative Logits
    wall
    -0.79
    hs
    -0.74
    âĸ¬
    -0.70
    ivities
    -0.70
    yards
    -0.68
    place
    -0.66
    chnology
    -0.64
    ience
    -0.61
    connected
    -0.61
    wb
    -0.60
    POSITIVE LOGITS
    orrow
    1.01
    EGA
    1.00
    obile
    0.92
    edia
    0.91
    oly
    0.91
    atis
    0.85
    ETH
    0.85
    AX
    0.84
    orph
    0.84
    BAT
    0.83
    Activations Density 0.010%

    No Known Activations