© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17282
    Prev
    Next
    INDEX
    Explanations

    phrases related to important figures and titles in official contexts

    oai_token-act-pair · gpt-3.5-turbo

    titles, names, and roles associated with individuals in a professional or organizational 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
     crumbling
    -0.73
     inh
    -0.65
     overrun
    -0.65
     buildup
    -0.64
     stomp
    -0.63
     densely
    -0.63
     inexpensive
    -0.63
     takeoff
    -0.62
     compressed
    -0.62
     tumble
    -0.62
    POSITIVE LOGITS
    Director
    1.33
    director
    1.31
    CEO
    1.23
    assador
    1.20
    Professor
    1.19
     Coordinator
    1.19
    Assistant
    1.17
     Director
    1.12
    Secretary
    1.12
    Senior
    1.12
    Activations Density 0.562%

    No Known Activations