© 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. 22427
    Prev
    Next
    INDEX
    Explanations

    words related to rules, regulations, and limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restrictions and limitations on freedoms

    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
    nexus
    -0.70
    dig
    -0.70
    00200000
    -0.68
    issance
    -0.68
    asus
    -0.66
    tein
    -0.66
    uscript
    -0.65
    apest
    -0.65
     Zeit
    -0.63
    char
    -0.63
    POSITIVE LOGITS
     imposed
    1.52
     restricting
    1.13
     placed
    1.12
     levied
    1.12
     prohibiting
    1.11
     enforced
    1.07
     preventing
    1.00
     inhib
    0.97
     exerted
    0.96
     lifted
    0.94
    Activations Density 0.138%

    No Known Activations