© 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. 7-RES-JB
    11. 1606
    Prev
    Next
    INDEX
    Explanations

    phrases related to waiting and taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving passive or contemplative 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
    EMS
    -0.85
    ãĤ¼
    -0.80
    UE
    -0.79
    videos
    -0.73
    specific
    -0.73
    entity
    -0.72
    HS
    -0.71
    currently
    -0.69
    FER
    -0.69
    enz
    -0.69
    POSITIVE LOGITS
     weep
    0.91
     stare
    0.89
     bury
    0.82
     relax
    0.81
     let
    0.81
     breathe
    0.81
     toes
    0.81
     pretend
    0.80
     evaluate
    0.80
     drown
    0.78
    Activations Density 0.199%

    No Known Activations