© 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. 8-RES-JB
    11. 11782
    Prev
    Next
    INDEX
    Explanations

    mentions of different sizes or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of size

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rique
    -0.82
    perty
    -0.80
    bara
    -0.75
    roit
    -0.74
     Michaels
    -0.72
    ILLE
    -0.71
    WP
    -0.69
     Rousse
    -0.69
    veyard
    -0.68
     Yor
    -0.67
    POSITIVE LOGITS
     scale
    1.00
     stature
    0.83
     circumference
    0.81
    capacity
    0.81
     discrepancy
    0.80
     footprint
    0.79
     proportion
    0.79
     intestine
    0.78
     constraints
    0.76
     size
    0.76
    Activations Density 0.054%

    No Known Activations