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. 2-RES-JB
    6. 4583
    Prev
    Next
    INDEX
    Explanations

    words related to systemic issues or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to systemic issues or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.77
    quer
    -0.76
    /+
    -0.71
    spell
    -0.67
    girl
    -0.67
    erb
    -0.67
    nery
    -0.67
    rug
    -0.67
    erer
    -0.67
    liest
    -0.66
    POSITIVE LOGITS
     systemic
    1.01
     racism
    0.85
    ultural
    0.83
     eleph
    0.82
     overhaul
    0.80
     earthqu
    0.76
     violations
    0.75
    onduct
    0.74
    ized
    0.74
     undermin
    0.73
    Activations Density 0.013%

    No Known Activations