© 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. 15777
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms with the letter 'B'

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'B' in various contexts

    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
    nces
    -0.69
     princ
    -0.65
    nels
    -0.65
    etheless
    -0.64
    Sov
    -0.63
     conduc
    -0.62
     laun
    -0.62
    essage
    -0.62
    repre
    -0.61
    aign
    -0.61
    POSITIVE LOGITS
     B
    2.89
    B
    1.92
     b
    1.61
     BA
    1.30
     BC
    1.30
    b
    1.28
     Ba
    1.23
     BB
    1.18
     IB
    1.15
    Bs
    1.14
    Activations Density 0.042%

    No Known Activations