© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5538
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people and places, especially related to official roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to requests, warnings, and decisions made by political figures or authorities

    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
    asus
    -0.73
    quin
    -0.69
    ravel
    -0.63
    ilogy
    -0.60
     artif
    -0.60
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.59
    illions
    -0.57
    ipes
    -0.56
     marvel
    -0.55
    aces
    -0.55
    POSITIVE LOGITS
     not
    1.19
     NOT
    1.02
    not
    0.99
     refrain
    0.97
     to
    0.94
     that
    0.89
     never
    0.89
     prohibiting
    0.87
     banning
    0.87
     forb
    0.84
    Activations Density 0.439%

    No Known Activations