© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1678
    Prev
    Next
    INDEX
    Explanations

    instances of actions being carried out, specifically involving sending someone somewhere or doing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sending or dispatching something or someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tions
    -0.71
    bone
    -0.63
     elig
    -0.62
    acles
    -0.61
    Ability
    -0.61
    aneous
    -0.61
    ById
    -0.60
    Mods
    -0.59
    natureconservancy
    -0.59
    iveness
    -0.58
    POSITIVE LOGITS
    pload
    0.84
     orbit
    0.78
    pless
    0.74
    iling
    0.74
     investigate
    0.72
     starve
    0.72
     oversee
    0.71
    velength
    0.70
    ggles
    0.69
     Pyongyang
    0.69
    Activations Density 0.114%

    No Known Activations