© 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 EvalsExportsinterp-engineNEWAPI 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. 11678
    Prev
    Next
    INDEX
    Explanations

    descriptions of fleeing or escaping from a location or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of fleeing or escaping from a situation

    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
    çĶ°
    -0.77
    wcs
    -0.76
    yi
    -0.74
    Names
    -0.70
    Link
    -0.67
     GOODMAN
    -0.66
    soDeliveryDate
    -0.65
     aloud
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
     msec
    -0.64
    POSITIVE LOGITS
     clut
    0.95
     collapsing
    0.87
     wrath
    0.82
     pursu
    0.82
     captivity
    0.82
     obscurity
    0.81
     persecution
    0.81
     confines
    0.79
     blaze
    0.78
     tyranny
    0.77
    Activations Density 0.301%

    No Known Activations