© 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. 11439
    Prev
    Next
    INDEX
    Explanations

    abbreviations with all upper case letters followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the acronym "UM"

    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
     Robin
    -0.73
     Stro
    -0.68
     brisk
    -0.65
     Sierra
    -0.64
     abras
    -0.63
     Argent
    -0.62
     gir
    -0.61
     compens
    -0.60
     Gret
    -0.60
     comb
    -0.59
    POSITIVE LOGITS
    UM
    4.26
    ums
    2.15
    um
    2.12
    UME
    1.90
    UMP
    1.55
     UM
    1.46
    umm
    1.40
    UL
    1.30
    UD
    1.30
    UB
    1.29
    Activations Density 0.010%

    No Known Activations