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. 9-RES-JB
    6. 17012
    Prev
    Next
    INDEX
    Explanations

    phrases related to fairness, health, and community well-being

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to fairness and accessibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bluff
    -0.97
    staking
    -0.79
     sheer
    -0.69
     overest
    -0.68
    secret
    -0.67
     caution
    -0.67
     treason
    -0.66
     whim
    -0.65
    ãĥ¯ãĥ³
    -0.65
    bsp
    -0.64
    POSITIVE LOGITS
     workplaces
    0.83
     everywhere
    0.81
     environments
    0.81
     wherever
    0.79
     prevail
    0.79
     outcomes
    0.74
     inclusive
    0.71
     2050
    0.70
     environment
    0.69
     amidst
    0.69
    Activations Density 0.438%

    No Known Activations