© 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. 11-RES-JB
    11. 2786
    Prev
    Next
    INDEX
    Explanations

    information related to computer architecture, specifically referring to 64-bit systems

    oai_token-act-pair · gpt-3.5-turbo

    references to computer architectures and specifications, particularly involving 64-bit and 32-bit systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icans
    -0.84
    andise
    -0.69
    ican
    -0.68
    ashtra
    -0.68
     Faw
    -0.63
     McH
    -0.63
    addock
    -0.62
     erect
    -0.62
    acus
    -0.61
    occ
    -0.57
    POSITIVE LOGITS
    bit
    1.56
    Bit
    1.30
    bits
    1.23
    BIT
    1.20
    GB
    1.16
     bit
    1.12
    KB
    1.12
    kB
    1.11
    Gb
    1.10
     bits
    1.08
    Activations Density 0.051%

    No Known Activations