© 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. 10-RES-JB
    6. 11354
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or presence of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that denote existence or presence of subjects

    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
    matter
    -0.82
    iliation
    -0.79
    isition
    -0.73
    gypt
    -0.71
    analysis
    -0.69
    usp
    -0.69
    aired
    -0.68
    ename
    -0.68
    ital
    -0.68
    illation
    -0.68
    POSITIVE LOGITS
     plenty
    1.24
     countless
    1.13
     lots
    1.12
     many
    1.12
     exceptions
    1.11
     dozens
    1.08
     several
    1.07
     few
    1.07
     occasions
    1.07
     innumerable
    1.05
    Activations Density 0.087%

    No Known Activations