© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17709
    Prev
    Next
    INDEX
    Explanations

    references to floating or suspension in space or air

    oai_token-act-pair · gpt-3.5-turbo

    instances 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heimer
    -0.77
    xx
    -0.74
     Cosponsors
    -0.72
    okers
    -0.71
    ENA
    -0.68
     à¨
    -0.64
    ä½ľ
    -0.64
    xxxx
    -0.60
    inges
    -0.60
    orial
    -0.60
    POSITIVE LOGITS
    flo
    0.88
    pole
    0.87
    plane
    0.84
     pond
    0.82
     afloat
    0.79
    chart
    0.77
     raft
    0.76
    boat
    0.73
    rily
    0.72
     floats
    0.72
    Activations Density 0.042%

    No Known Activations