© 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. 15206
    Prev
    Next
    INDEX
    Explanations

    French numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    formatted numerical values and identifiers related to technology and software

    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
    kinson
    -0.68
     shudder
    -0.66
    gerald
    -0.65
    urga
    -0.64
    auga
    -0.63
    essor
    -0.62
    erella
    -0.61
     showc
    -0.60
     Samar
    -0.60
     adam
    -0.59
    POSITIVE LOGITS
    GHz
    0.95
    ĪĴ
    0.85
    otide
    0.84
     GHz
    0.79
    agonists
    0.73
    ibrary
    0.72
    bsp
    0.70
    thirds
    0.69
    048
    0.67
    GBT
    0.67
    Activations Density 0.246%

    No Known Activations