© 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. 6-RES-JB
    11. 570
    Prev
    Next
    INDEX
    Explanations

    mentions of computer processors with multiple cores

    oai_token-act-pair · gpt-3.5-turbo

    references to multi-core processors and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.74
    etheless
    -0.72
    atar
    -0.72
    ¬¼
    -0.70
    ¹
    -0.70
     Ukrain
    -0.70
    icter
    -0.69
    atan
    -0.66
    Ĥİ
    -0.66
    aution
    -0.66
    POSITIVE LOGITS
    core
    0.97
    xit
    0.91
    opsis
    0.78
    lli
    0.75
    boot
    0.72
    rs
    0.72
    rite
    0.70
    nces
    0.69
     processor
    0.68
    clave
    0.67
    Activations Density 0.013%

    No Known Activations