© 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. 1906
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving or exiting

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of leaving or moving away from a situation

    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
     heartbeat
    -0.63
    ery
    -0.59
    ¥µ
    -0.59
    inski
    -0.58
    asus
    -0.58
    Interstitial
    -0.57
     artisan
    -0.56
     Meridian
    -0.55
     lig
    -0.53
     Khe
    -0.53
    POSITIVE LOGITS
    stretched
    1.01
    door
    0.94
    doors
    0.93
    fitted
    0.84
    smart
    0.83
    ta
    0.82
    rage
    0.81
    raged
    0.80
    posts
    0.79
    bred
    0.76
    Activations Density 0.029%

    No Known Activations