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. 7-RES-JB
    6. 6690
    Prev
    Next
    INDEX
    Explanations

    references to voluntary work or acts of volunteering

    oai_token-act-pair · gpt-3.5-turbo

    references to volunteerism and volunteer activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fixes
    -0.87
    acles
    -0.76
    erella
    -0.75
    hetti
    -0.74
    etus
    -0.69
    etr
    -0.68
    rums
    -0.66
    metics
    -0.66
    estamp
    -0.65
    utra
    -0.64
    POSITIVE LOGITS
    unte
    1.15
     volunteering
    0.95
     Volunteers
    0.93
     firefighter
    0.90
     volunteer
    0.90
     coordinator
    0.80
    intern
    0.79
     battalion
    0.78
     volunteers
    0.78
     Volunteer
    0.72
    Activations Density 0.025%

    No Known Activations