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. 11-RES-JB
    6. 19914
    Prev
    Next
    INDEX
    Explanations

    the phrase "a bit of" followed by a description or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of "a bit" or "little bit."

    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
    osponsors
    -0.60
    ivable
    -0.60
    ulkan
    -0.58
    abad
    -0.58
     Scores
    -0.57
    idth
    -0.55
     Sins
    -0.55
    orthy
    -0.55
    yss
    -0.54
    ¥ŀ
    -0.53
    POSITIVE LOGITS
    terness
    0.98
     of
    0.97
    ching
    0.87
    mask
    0.83
     thereof
    0.83
    umen
    0.81
     more
    0.78
     taller
    0.77
     longer
    0.76
     nicer
    0.76
    Activations Density 0.051%

    No Known Activations