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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 17545
    Prev
    Next
    INDEX
    Explanations

    mentions of people who have shown courage or bravery

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with significant contributions or impacts

    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
    reporting
    -0.77
     scheduling
    -0.72
    availability
    -0.72
     Inspection
    -0.70
     airing
    -0.68
     reservations
    -0.68
    Regarding
    -0.68
     Setup
    -0.67
    itant
    -0.67
    uming
    -0.67
    POSITIVE LOGITS
     overcame
    1.64
     sacrificed
    1.56
     died
    1.50
     perished
    1.49
     risked
    1.44
     defied
    1.43
     survived
    1.42
     fought
    1.35
     succeeded
    1.35
     deserved
    1.33
    Activations Density 0.434%

    No Known Activations