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. 19432
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of communication and organization, such as advocacy, journalism, and education

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social interaction, advocacy, and collaboration

    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
    ãĥĥãĥī
    -0.82
    BuyableInstoreAndOnline
    -0.78
    Hig
    -0.70
    ibel
    -0.69
    ewitness
    -0.68
     earthqu
    -0.67
     Baz
    -0.67
    hest
    -0.65
    otted
    -0.63
    abase
    -0.62
    POSITIVE LOGITS
     strategies
    1.29
     techniques
    1.28
     schemes
    1.24
     mechanisms
    1.18
     practices
    1.16
     tactics
    1.15
    utics
    1.08
     regimes
    1.07
     methods
    1.05
     principles
    1.03
    Activations Density 0.338%

    No Known Activations