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. 10624
    Prev
    Next
    INDEX
    Explanations

    the term "ebb"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "bb"

    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
     honoring
    -0.69
     sealing
    -0.65
     utilizing
    -0.64
     nano
    -0.62
     capac
    -0.62
     Protector
    -0.62
     prescriptions
    -0.60
     Nano
    -0.60
     honor
    -0.60
     memory
    -0.59
    POSITIVE LOGITS
    bb
    4.23
    BB
    2.01
    bc
    1.50
    bf
    1.45
    bm
    1.33
    bs
    1.33
    bd
    1.32
    kk
    1.32
    dd
    1.31
    cca
    1.24
    Activations Density 0.014%

    No Known Activations