© 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. 10-RES-JB
    11. 3275
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement out of a place

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being removed or escorted from a location

    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
    avorite
    -0.69
    Berry
    -0.63
     Conservatives
    -0.62
     Percent
    -0.60
    antine
    -0.55
    ĻĤ
    -0.51
    ilies
    -0.51
     Essential
    -0.51
    geries
    -0.49
    inical
    -0.49
    POSITIVE LOGITS
    fitted
    1.45
    wards
    1.39
    stretched
    1.27
    ta
    1.24
     onto
    1.07
    doors
    1.07
    posts
    0.98
    skirts
    0.98
     of
    0.94
    smart
    0.93
    Activations Density 0.058%

    No Known Activations