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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15857
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names, especially related to people, organizations, and prizes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of women's issues or perspectives in a historical or socio-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
    Magikarp
    -0.81
    ERC
    -0.79
     masc
    -0.78
     unic
    -0.76
     IoT
    -0.73
    STEM
    -0.72
    à¼
    -0.72
    Applications
    -0.72
    icons
    -0.71
     blockers
    -0.71
    POSITIVE LOGITS
     memoir
    1.73
     autobiography
    1.57
     excerpts
    1.39
     biography
    1.36
     autobi
    1.35
     interviews
    1.32
     recounted
    1.24
     excerpt
    1.23
     chron
    1.23
     recol
    1.23
    Activations Density 0.592%

    No Known Activations