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. 5-RES-JB
    6. 3731
    Prev
    Next
    INDEX
    Explanations

    references to the country of Iran and its governmental system

    oai_token-act-pair · gpt-3.5-turbo

    references to the Iranian government and its associated entities

    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
    lished
    -0.88
    illard
    -0.88
    leground
    -0.86
    chat
    -0.86
    VEL
    -0.84
    fill
    -0.82
    cial
    -0.82
    erk
    -0.82
    shaw
    -0.81
    iatrics
    -0.81
    POSITIVE LOGITS
     consulate
    0.83
     dissidents
    0.83
    istani
    0.82
     Revolutionary
    0.81
     regime
    0.78
     embassy
    0.78
     influence
    0.75
     hegemony
    0.73
     exile
    0.73
     oil
    0.72
    Activations Density 0.008%

    No Known Activations