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. 15363
    Prev
    Next
    INDEX
    Explanations

    phrases related to live performances and audience engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions related to event planning and coordination

    oai_token-act-pair · gpt-3.5-turbo
    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
    ģĸ
    -0.72
    Economic
    -0.72
    osate
    -0.71
    agate
    -0.67
    Path
    -0.65
     Growth
    -0.65
    raft
    -0.65
    rowth
    -0.64
    byss
    -0.64
    growing
    -0.64
    POSITIVE LOGITS
     audience
    1.47
     backstage
    1.45
     onstage
    1.43
     microphones
    1.40
     spectators
    1.39
     announcer
    1.35
     narration
    1.33
     subtitles
    1.33
     audiences
    1.30
     viewers
    1.30
    Activations Density 0.945%

    No Known Activations