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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 2100
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational institutions or organizations within a community

    oai_token-act-pair · gpt-3.5-turbo

    references to community organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argon
    -0.78
    thing
    -0.74
    nings
    -0.73
    Downloadha
    -0.72
    glers
    -0.72
    nian
    -0.69
    etsk
    -0.69
    ames
    -0.69
    rosc
    -0.68
    zzy
    -0.66
    POSITIVE LOGITS
     cohesion
    0.97
     outreach
    0.94
     engagement
    0.85
     relations
    0.82
    ãĤ©
    0.80
     councils
    0.77
     Supported
    0.75
     amenities
    0.75
     colleges
    0.73
     policing
    0.73
    Activations Density 0.031%

    No Known Activations