© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7942
    Prev
    Next
    INDEX
    Explanations

    quantitative information related to numbers and values

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and their context within the document

    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
    leys
    -0.70
     campaigns
    -0.67
    ighting
    -0.67
    ellar
    -0.61
     libraries
    -0.59
    rower
    -0.58
    hester
    -0.58
    arma
    -0.58
     dealings
    -0.57
    ESE
    -0.57
    POSITIVE LOGITS
     ¥
    0.91
     centimeters
    0.79
     9000
    0.77
    66666666
    0.76
     $
    0.75
     nominal
    0.75
    900
    0.74
     1850
    0.74
    999
    0.73
    500
    0.73
    Activations Density 0.539%

    No Known Activations