Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9594
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and orders

    oai_token-act-pair · gpt-3.5-turbo

    references to immigration and legal status issues

    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
     Alas
    -0.75
    etheless
    -0.75
     Adds
    -0.67
     "{
    -0.64
    roxy
    -0.63
     Often
    -0.60
     Verge
    -0.60
    APS
    -0.60
     Contrast
    -0.60
     eagerly
    -0.59
    POSITIVE LOGITS
     gotta
    1.39
     ain
    1.21
     gonna
    1.08
    're
    1.06
     wanna
    1.06
     got
    1.01
     fuckin
    0.95
     owe
    0.89
     deserve
    0.87
     ought
    0.87
    Activations Density 0.304%

    No Known Activations