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

    Neuronpedia

    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. 19206
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations related to medical terms or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "CH" associated with various contexts

    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
     vib
    -0.66
     Raf
    -0.65
     boundaries
    -0.65
     Fo
    -0.63
     Xer
    -0.63
     Aberdeen
    -0.62
     Reed
    -0.62
     Lys
    -0.61
     Wolfe
    -0.61
     Nil
    -0.60
    POSITIVE LOGITS
    CH
    4.09
    CHA
    2.19
    CHO
    2.02
     CH
    1.84
    ch
    1.79
    ches
    1.70
    CHR
    1.59
    ched
    1.58
    ching
    1.55
    che
    1.51
    Activations Density 0.012%

    No Known Activations