© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6258
    Prev
    Next
    INDEX
    Explanations

    references to various types of scientists, including physicists, mathematicians, and philosophers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various scientific professions, particularly in physics and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ients
    -0.69
    ills
    -0.68
    houses
    -0.68
    tons
    -0.67
     iPads
    -0.64
     Commands
    -0.63
    days
    -0.63
     legs
    -0.61
     platforms
    -0.60
     orders
    -0.60
    POSITIVE LOGITS
     physicist
    2.36
     historian
    2.25
     journalist
    2.23
     mathematician
    2.18
     novelist
    2.17
     biologist
    2.16
     philosopher
    2.15
     filmmaker
    2.12
     astronomer
    2.10
     scholar
    2.08
    Activations Density 0.067%

    No Known Activations