© 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. 11-RES-JB
    11. 20926
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving a location or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in relation to actions of leaving or exiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agu
    -0.79
    meric
    -0.75
    rand
    -0.75
    iversal
    -0.74
    amac
    -0.73
    omever
    -0.71
    ãĥĥãĥĪ
    -0.69
    én
    -0.67
    VERSION
    -0.67
    var
    -0.66
    POSITIVE LOGITS
     fray
    1.35
     confines
    1.21
     equation
    1.18
     premises
    1.15
     scene
    1.07
     fold
    1.04
     country
    1.00
     door
    0.96
     courtroom
    0.96
     workforce
    0.89
    Activations Density 0.149%

    No Known Activations