© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3214
    Prev
    Next
    INDEX
    Explanations

    references to specific computer hardware specifications, specifically focusing on the term 'bit'

    oai_token-act-pair · gpt-3.5-turbo

    references to "bit" and its various numerical specifications in computing

    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
    foreseen
    -0.82
    ammad
    -0.82
    itual
    -0.77
    qqa
    -0.73
    ocrates
    -0.72
    idelines
    -0.72
    ouf
    -0.69
    ashtra
    -0.69
    kefeller
    -0.69
    responsible
    -0.66
    POSITIVE LOGITS
     integers
    1.03
     integer
    0.95
     version
    0.78
     versions
    0.77
     equivalents
    0.72
     AES
    0.71
     auth
    0.70
     chars
    0.69
     unsigned
    0.69
     penetration
    0.69
    Activations Density 0.019%

    No Known Activations