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. 8532
    Prev
    Next
    INDEX
    Explanations

    political and societal terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to media and societal 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
    iHUD
    -0.71
    ãĤ´ãĥ³
    -0.67
    ãĤ¡
    -0.61
    arget
    -0.59
     Incarn
    -0.57
    size
    -0.57
     ç¥ŀ
    -0.56
    long
    -0.56
     Osc
    -0.56
    ãĥ¼ãĥ«
    -0.55
    POSITIVE LOGITS
     guys
    1.33
     guy
    1.30
     idiots
    1.16
     folks
    1.13
     admins
    1.09
     devs
    1.07
     dudes
    1.07
     commenters
    1.06
     thugs
    1.02
     commentators
    1.00
    Activations Density 0.721%

    No Known Activations