© 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 EvalsExportsinterp-engineNEWAPI 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. 974
    Prev
    Next
    INDEX
    Explanations

    numerical data patterns, such as percentages and monetary values, along with mentions of organizations and locations

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics, particularly relating to financial figures and percentages

    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
    iliated
    -0.73
    inos
    -0.72
    inas
    -0.70
    cffff
    -0.67
    ilater
    -0.66
    ());
    -0.64
    icides
    -0.63
    endas
    -0.63
     reconc
    -0.61
    itialized
    -0.60
    POSITIVE LOGITS
    ¼
    0.71
    Ģ
    0.68
    Lower
    0.68
    Wide
    0.66
    Deploy
    0.65
    ĺ
    0.64
    Dual
    0.64
    ACE
    0.64
    Word
    0.64
    ı
    0.64
    Activations Density 0.206%

    No Known Activations