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. 24314
    Prev
    Next
    INDEX
    Explanations

    references to political roles and actions related to government and leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to female leadership roles, specifically in a political context

    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
     [/
    -0.72
    ====
    -0.66
    quickShipAvailable
    -0.65
     Saying
    -0.64
     saying
    -0.63
    ================
    -0.63
     Falling
    -0.62
     Cancel
    -0.62
    Pause
    -0.61
     SAY
    -0.61
    POSITIVE LOGITS
     oversaw
    1.53
     helped
    1.39
     ensured
    1.27
     facilitated
    1.26
     aided
    1.26
     battled
    1.23
     guided
    1.23
     spearheaded
    1.23
     steered
    1.22
     interacted
    1.19
    Activations Density 0.344%

    No Known Activations