© 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. 10254
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and decisions made by an individual

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the verb "do" in various contexts

    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
    ãĤ´ãĥ³
    -0.81
    ONSORED
    -0.75
    ItemTracker
    -0.69
    ESA
    -0.68
    raltar
    -0.67
    isu
    -0.65
    é¾įå¥ij士
    -0.64
    uably
    -0.60
    Leader
    -0.59
    USS
    -0.59
    POSITIVE LOGITS
    zed
    0.93
    pez
    0.92
     wonders
    0.91
    vet
    0.88
     everything
    0.87
     NOT
    0.85
    omsday
    0.84
     homework
    0.82
     not
    0.82
    oms
    0.81
    Activations Density 0.098%

    No Known Activations