© 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. 9391
    Prev
    Next
    INDEX
    Explanations

    patterns of characters or codes that don't correspond to meaningful words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    sequences of 'x' characters followed by numerical values

    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
     Pru
    -0.75
    sburgh
    -0.75
    DERR
    -0.74
    zona
    -0.74
     Lauder
    -0.73
    ãĥĦ
    -0.68
    maid
    -0.67
    awaru
    -0.66
     Garry
    -0.66
    assetsadobe
    -0.64
    POSITIVE LOGITS
    aminer
    0.94
    Ry
    0.86
    avier
    0.85
    posed
    0.84
    iii
    0.81
    amination
    0.81
    terday
    0.80
    86
    0.79
    cb
    0.78
    kb
    0.78
    Activations Density 0.022%

    No Known Activations