© 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. 0-RES-JB
    11. 15275
    Prev
    Next
    INDEX
    Explanations

    numerical values related to data storage and memory capacity

    oai_token-act-pair · gpt-3.5-turbo

    references to storage capacity in gigabytes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allaah
    -0.71
     Mend
    -0.66
     tal
    -0.66
     tents
    -0.66
     Frey
    -0.65
     Ill
    -0.65
     Quin
    -0.65
     Tay
    -0.65
     Coh
    -0.64
     Allah
    -0.63
    POSITIVE LOGITS
    GB
    4.14
     GB
    2.70
    gb
    2.33
    TB
    2.13
    MB
    1.95
    Gb
    1.87
    GBT
    1.71
    KB
    1.57
    GD
    1.46
    GW
    1.33
    Activations Density 0.017%

    No Known Activations