© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11868
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "COO" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or entity, suggesting a focus on a particular company or brand

    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
     seniors
    -0.68
    lishes
    -0.66
     travel
    -0.66
     Les
    -0.65
    folk
    -0.65
     lif
    -0.64
     cons
    -0.62
    chal
    -0.62
     Fathers
    -0.62
    chen
    -0.62
    POSITIVE LOGITS
    OO
    4.19
    oo
    1.95
    OOOO
    1.93
    OOOOOOOO
    1.75
    FO
    1.44
    OOK
    1.43
    oos
    1.42
    ooo
    1.41
    OH
    1.39
    oooo
    1.35
    Activations Density 0.011%

    No Known Activations