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. 11-RES-JB
    6. 8606
    Prev
    Next
    INDEX
    Explanations

    mentions of social activities, such as spending time with friends, enjoying music, and building community through conversation and coffee

    oai_token-act-pair · gpt-3.5-turbo

    the presence of elements related to culture, creativity, and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ormonal
    -0.80
    20439
    -0.78
    achment
    -0.78
    utable
    -0.75
    Phase
    -0.74
    ministic
    -0.74
    ©¶æ¥µ
    -0.73
    PsyNetMessage
    -0.72
    etsk
    -0.70
    istar
    -0.69
    POSITIVE LOGITS
     crafts
    1.36
     cuisine
    1.27
     arts
    1.24
     storytelling
    1.20
     entertainment
    1.19
     poetry
    1.18
     hospitality
    1.15
     spirituality
    1.15
     sculpture
    1.15
     photography
    1.15
    Activations Density 0.218%

    No Known Activations