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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20625
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions related to different types of therapies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various forms of therapy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.77
    ouver
    -0.73
    lihood
    -0.73
    ership
    -0.69
     Citizenship
    -0.66
    print
    -0.62
    ãĥĥãĥī
    -0.62
    umbers
    -0.62
    poll
    -0.62
     Citiz
    -0.62
    POSITIVE LOGITS
     sessions
    0.96
     session
    0.86
    otherapy
    0.85
    apist
    0.82
     regimen
    0.81
    apy
    0.79
    utic
    0.78
     therapy
    0.78
     treatments
    0.77
    ilitating
    0.76
    Activations Density 0.049%

    No Known Activations