© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2837
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initials within text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to abbreviations and acronyms

    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
    wine
    -0.80
    views
    -0.78
    Gh
    -0.67
    Ge
    -0.64
    ende
    -0.63
     Wine
    -0.63
    izons
    -0.63
    raf
    -0.62
    gpu
    -0.61
    Va
    -0.61
    POSITIVE LOGITS
     acronym
    4.18
     acron
    3.02
     abbre
    2.86
     initials
    2.44
     abbrevi
    2.02
    viation
    1.70
     jargon
    1.39
     nickname
    1.39
    ËĪ
    1.39
     alphabet
    1.34
    Activations Density 0.033%

    No Known Activations