Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16131
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations containing 'B'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'B'

    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
     warr
    -0.63
     stagnation
    -0.63
     continu
    -0.61
     adamant
    -0.59
     princ
    -0.59
     stuffing
    -0.59
     sund
    -0.58
     pudding
    -0.58
     smelling
    -0.58
    entin
    -0.57
    POSITIVE LOGITS
    B
    3.25
    Bs
    2.42
    b
    1.79
    BB
    1.72
     B
    1.68
    BS
    1.65
    BG
    1.64
    BR
    1.62
    BN
    1.58
    BW
    1.57
    Activations Density 0.035%

    No Known Activations