© 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. 8-RES-JB
    11. 10259
    Prev
    Next
    INDEX
    Explanations

    action verbs related to managing, organizing, maintaining, and enforcing tasks

    oai_token-act-pair · gpt-3.5-turbo

    actions related to management and preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cas
    -0.70
    imura
    -0.67
    liest
    -0.67
    usra
    -0.67
    vs
    -0.65
    culus
    -0.65
    atus
    -0.64
    cus
    -0.63
    ev
    -0.63
    kernel
    -0.62
    POSITIVE LOGITS
     alike
    1.09
     respectively
    0.91
     portions
    0.69
     aspects
    0.68
    enance
    0.67
     accordingly
    0.65
     depending
    0.61
     behalf
    0.59
     processes
    0.58
     certain
    0.58
    Activations Density 0.250%

    No Known Activations