© 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. 24094
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing tasks or achieving goals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating execution or completion of actions

    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
    advert
    -0.63
    ãĥ©ãĥ³
    -0.61
     Variant
    -0.60
    ãĤ¦ãĤ¹
    -0.59
    drop
    -0.59
    ango
    -0.57
    username
    -0.57
    tones
    -0.57
     QR
    -0.56
    factor
    -0.56
    POSITIVE LOGITS
     ASAP
    0.87
     efficiently
    0.82
     sooner
    0.79
    .–
    0.73
     peacefully
    0.72
     quicker
    0.71
     smoothly
    0.68
     offensively
    0.67
     economically
    0.65
     cheaply
    0.65
    Activations Density 0.198%

    No Known Activations