© 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. 9-RES-JB
    11. 7517
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are involved in various types of activities or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to engagement in various activities or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    installed
    -0.76
     Ended
    -0.75
    ended
    -0.75
    ãĥ¼ãĥ³
    -0.74
    selves
    -0.73
    lights
    -0.72
    IELD
    -0.70
     Borders
    -0.69
    oise
    -0.69
    ario
    -0.69
    POSITIVE LOGITS
     conversation
    0.98
     continual
    0.98
     vigorous
    0.95
     reckless
    0.93
     willful
    0.92
     consensual
    0.91
     banter
    0.90
     concerted
    0.90
     subter
    0.89
     wasteful
    0.89
    Activations Density 0.139%

    No Known Activations