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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22270
    Prev
    Next
    INDEX
    Explanations

    user information profiles, including usernames, countries, dates joined, and number of posts

    oai_token-act-pair · gpt-3.5-turbo

    information related to user profiles and activity metrics

    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
    agos
    -0.78
    hetically
    -0.70
    selves
    -0.70
    buster
    -0.70
    awed
    -0.68
    busters
    -0.66
    £ı
    -0.66
     royalty
    -0.65
    oths
    -0.64
    ueller
    -0.64
    POSITIVE LOGITS
     Joined
    1.16
     October
    0.94
     July
    0.94
     November
    0.93
     August
    0.92
     March
    0.91
     June
    0.91
     February
    0.90
     December
    0.90
     January
    0.89
    Activations Density 0.013%

    No Known Activations