© 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. 10-RES-JB
    11. 16283
    Prev
    Next
    INDEX
    Explanations

    tech-related terms and company names

    oai_token-act-pair · gpt-3.5-turbo

    specific brand names, companies, or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usher
    -0.79
     Hague
    -0.78
    bishop
    -0.76
    epad
    -0.76
    oshop
    -0.75
    emaker
    -0.71
    ridor
    -0.70
    dad
    -0.69
    apego
    -0.69
     Mourinho
    -0.69
    POSITIVE LOGITS
     clones
    1.23
     employees
    1.19
     installations
    1.17
     products
    1.14
     clients
    1.14
     instances
    1.13
     entries
    1.12
     members
    1.12
     staffers
    1.11
     locations
    1.11
    Activations Density 0.409%

    No Known Activations