© 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
    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. 21765
    Prev
    Next
    INDEX
    Explanations

    phrases related to things starting or beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "taking off" in various contexts

    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
    Gall
    -0.67
    ISM
    -0.66
    OTT
    -0.65
    obb
    -0.64
    olson
    -0.63
    Champ
    -0.62
    xtap
    -0.62
    itia
    -0.62
    ãĤ§
    -0.62
    oby
    -0.61
    POSITIVE LOGITS
    spr
    0.91
    site
    0.84
    shoot
    0.83
    screen
    0.82
     pist
    0.79
    loaded
    0.74
    wards
    0.74
     shotguns
    0.73
    ibaba
    0.72
    loading
    0.72
    Activations Density 0.058%

    No Known Activations