© 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. 9-RES-JB
    11. 3515
    Prev
    Next
    INDEX
    Explanations

    product or brand names related to technology products

    oai_token-act-pair · gpt-3.5-turbo

    trademark symbols and specific branded products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acle
    -0.70
    esses
    -0.69
    liness
    -0.68
    oids
    -0.68
    seless
    -0.68
    ibel
    -0.67
    urger
    -0.67
    ameda
    -0.67
    wright
    -0.66
    elo
    -0.65
    POSITIVE LOGITS
    ternity
    0.77
    Fram
    0.68
    Plus
    0.66
    Vision
    0.66
    Wide
    0.65
    ¢
    0.64
    Ultra
    0.63
    ï¸ı
    0.62
    ãĤº
    0.62
    culosis
    0.61
    Activations Density 0.033%

    No Known Activations