© 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. 2-RES-JB
    11. 9219
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Avonte" and "Pai"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "onte"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andise
    -0.82
    dar
    -0.81
    rera
    -0.71
    bar
    -0.70
    otomy
    -0.68
    nesses
    -0.68
    atform
    -0.65
    imony
    -0.65
    ilial
    -0.65
    alm
    -0.65
    POSITIVE LOGITS
    veyard
    0.83
    chnology
    0.78
    Äį
    0.78
    onte
    0.76
    urus
    0.74
    achers
    0.70
    GBT
    0.69
    lees
    0.69
    zzi
    0.69
    issance
    0.68
    Activations Density 0.021%

    No Known Activations