© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    keywords related to enabling or permitting actions to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate enabling capabilities or functionalities

    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
    女
    -0.76
    è¦ļéĨĴ
    -0.73
    ãĥĩãĤ£
    -0.71
    schild
    -0.69
    lie
    -0.69
    xon
    -0.68
    ãĤ¡
    -0.65
    å°Ĩ
    -0.65
    ãĤ©
    -0.65
    geist
    -0.64
    POSITIVE LOGITS
     us
    1.21
     them
    0.99
     users
    0.90
     for
    0.90
     him
    0.87
     developers
    0.85
     researchers
    0.83
     me
    0.80
     anyone
    0.79
     seamless
    0.79
    Activations Density 0.096%

    No Known Activations