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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 23416
    Prev
    Next
    INDEX
    Explanations

    references to boards of directors or similar governing bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to various boards, educational institutions, and their governance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ashtra
    -0.73
    aan
    -0.71
    auna
    -0.68
    nah
    -0.68
    ibe
    -0.66
    catentry
    -0.66
     Ãľ
    -0.65
    hematically
    -0.64
    iosity
    -0.63
    vell
    -0.63
    POSITIVE LOGITS
     Directors
    0.94
     directors
    0.79
     Governors
    0.78
     Commissioners
    0.76
     commissions
    0.71
    ature
    0.71
     trustees
    0.69
    visors
    0.69
    estate
    0.68
    office
    0.68
    Activations Density 0.116%

    No Known Activations