© 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. 8-RES-JB
    11. 106
    Prev
    Next
    INDEX
    Explanations

    words related to legal or biological terms ending with 'ase'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various conditions or types of disease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersive
    -0.89
    icum
    -0.86
    arious
    -0.85
    nesday
    -0.78
    enegger
    -0.74
    undy
    -0.73
    romeda
    -0.70
    ersen
    -0.70
    ancial
    -0.69
    ¥ŀ
    -0.69
    POSITIVE LOGITS
    xual
    1.76
    ño
    1.06
    lled
    0.89
    ñ
    0.85
    hift
    0.85
    lly
    0.84
     inhibitors
    0.83
    lling
    0.77
     inhibitor
    0.72
    berries
    0.71
    Activations Density 0.044%

    No Known Activations