© 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. 10-RES-JB
    11. 17480
    Prev
    Next
    INDEX
    Explanations

    phrases related to forming groups or coalitions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "form" in various contexts related to creating or establishing entities or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bye
    -0.71
    BILITY
    -0.68
    rendered
    -0.65
    yssey
    -0.64
    import
    -0.63
    iolet
    -0.61
    gee
    -0.61
    ubb
    -0.61
    iness
    -0.60
    ey
    -0.60
    POSITIVE LOGITS
    ulates
    1.26
     alliances
    1.10
    ulating
    1.08
    ulate
    1.06
    aldehyde
    0.98
     friendships
    0.93
    idable
    0.93
    ulas
    0.92
     partnerships
    0.89
    ulated
    0.86
    Activations Density 0.050%

    No Known Activations