© 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. 11-RES-JB
    11. 7615
    Prev
    Next
    INDEX
    Explanations

    phrases related to escaping or avoiding something

    oai_token-act-pair · gpt-3.5-turbo

    references to escape or confinement

    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
    owned
    -0.77
    #$#$
    -0.73
    thood
    -0.73
    SHIP
    -0.71
    conn
    -0.70
    SPONSORED
    -0.69
    CE
    -0.69
    Goal
    -0.69
    abee
    -0.68
    Account
    -0.68
    POSITIVE LOGITS
     onslaught
    1.46
     wrath
    1.37
     brunt
    1.36
     horrors
    1.33
     pressures
    1.31
     consequences
    1.26
     dangers
    1.26
     stresses
    1.24
     pitfalls
    1.22
     hars
    1.21
    Activations Density 0.250%

    No Known Activations