© 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. 6-RES-JB
    11. 17682
    Prev
    Next
    INDEX
    Explanations

    phrases related to action or movement out of a specific location or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "get out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cious
    -0.62
     heartbeat
    -0.61
    inski
    -0.58
    cius
    -0.56
     Jinping
    -0.55
     issuer
    -0.54
    onding
    -0.53
     capt
    -0.53
     Rounds
    -0.53
     arsen
    -0.52
    POSITIVE LOGITS
    stretched
    0.96
    smart
    0.88
    skirts
    0.86
    rage
    0.86
    door
    0.85
    doors
    0.84
    fitted
    0.82
    ta
    0.81
    posts
    0.78
    bur
    0.76
    Activations Density 0.036%

    No Known Activations