© 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. 9454
    Prev
    Next
    INDEX
    Explanations

    words related to legal and governmental institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to disciplinary actions and related institutional responses

    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
     favors
    -0.84
     favoring
    -0.80
     signaled
    -0.80
     labeled
    -0.79
    eus
    -0.77
    colored
    -0.76
     utilized
    -0.74
    TPP
    -0.74
     utilize
    -0.74
     utilizes
    -0.73
    POSITIVE LOGITS
     NSW
    1.47
     Queensland
    1.33
     NRL
    1.27
     Victorian
    1.25
     Scottish
    1.23
     Perth
    1.23
     Surrey
    1.21
     Auckland
    1.19
     Brisbane
    1.17
     Yorkshire
    1.17
    Activations Density 0.322%

    No Known Activations