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. 17068
    Prev
    Next
    INDEX
    Explanations

    phrases related to news stories covering the LGBT community globally

    oai_token-act-pair · gpt-3.5-turbo

    references to global events or topics related to the LGBT community

    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
     nowhere
    -0.61
     bottleneck
    -0.59
     earlier
    -0.56
     harsher
    -0.55
     dime
    -0.53
     worse
    -0.53
     bigger
    -0.53
     withdrawals
    -0.53
     later
    -0.53
     IPO
    -0.52
    POSITIVE LOGITS
    ãĥĦ
    0.70
    ¥
    0.70
    rave
    0.69
    eem
    0.69
    ¯¯¯¯¯¯¯¯
    0.68
    oise
    0.67
    ractor
    0.66
    assador
    0.65
    lete
    0.64
    ï
    0.64
    Activations Density 0.590%

    No Known Activations