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. 22023
    Prev
    Next
    INDEX
    Explanations

    references to the country Saudi Arabia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Saudi Arabia and its associations

    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
    mble
    -0.90
    schild
    -0.88
    eon
    -0.78
    lest
    -0.76
     Myster
    -0.71
     Puzz
    -0.71
    estern
    -0.70
    matter
    -0.69
     Matter
    -0.68
     Repair
    -0.67
    POSITIVE LOGITS
     Arabia
    1.89
     Arabian
    1.49
     Aram
    1.12
    istani
    0.89
     princes
    0.86
     nationals
    0.82
     Abdullah
    0.79
     Arab
    0.79
    istan
    0.77
     prince
    0.74
    Activations Density 0.010%

    No Known Activations