© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and authority

    oai_token-act-pair · gpt-3.5-turbo

    significant events or announcements

    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
     ageing
    -0.80
     concess
    -0.71
    ocrates
    -0.70
     practise
    -0.65
     His
    -0.65
    isable
    -0.64
     his
    -0.64
     binds
    -0.64
    yip
    -0.63
     recognise
    -0.63
    POSITIVE LOGITS
    âĢ
    1.31
    didn
    0.99
     âĢ
    0.94
    ðŁĺ
    0.90
     Didn
    0.87
    âĻ¦
    0.85
    Instead
    0.85
    they
    0.84
     Turns
    0.83
    ãĢ
    0.83
    Activations Density 1.121%

    No Known Activations