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. 1-RES-JB
    6. 18086
    Prev
    Next
    INDEX
    Explanations

    concepts related to floating or suspended states

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "floating" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anasia
    -0.78
    aldi
    -0.76
    ause
    -0.74
    older
    -0.73
    heimer
    -0.73
    sin
    -0.71
    anan
    -0.71
    avez
    -0.70
    sen
    -0.68
    Ur
    -0.68
    POSITIVE LOGITS
     floating
    1.22
     Floating
    1.04
     floated
    0.88
     floats
    0.86
     float
    0.84
    flo
    0.84
     flo
    0.79
    Flo
    0.77
    ©¶æ¥µ
    0.77
     overboard
    0.76
    Activations Density 0.009%

    No Known Activations