© 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. 0-RES-JB
    11. 14782
    Prev
    Next
    INDEX
    Explanations

    words related to various types of activities and operations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various activities, particularly those with implications for organization or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estamp
    -0.72
    wn
    -0.72
    utch
    -0.68
     nailed
    -0.65
    angled
    -0.65
    Bomb
    -0.64
     Reborn
    -0.64
    font
    -0.63
    orned
    -0.63
    oil
    -0.62
    POSITIVE LOGITS
     activities
    3.53
     Activities
    2.81
     activity
    2.40
     Activity
    1.81
     actions
    1.81
     pursuits
    1.62
     endeavors
    1.61
     behaviors
    1.61
     practices
    1.58
    activity
    1.56
    Activations Density 0.017%

    No Known Activations