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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 18196
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "El Salvador"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'El' followed by a geographic location, highlighting various places in Central America and Mexico

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.88
    )=(
    -0.76
    hire
    -0.76
     Pict
    -0.73
    nant
    -0.72
     Anthem
    -0.72
    henko
    -0.71
    NOW
    -0.71
    SourceFile
    -0.69
    displayText
    -0.69
    POSITIVE LOGITS
    azer
    0.96
    ving
    0.95
    igible
    0.92
    bert
    0.88
    isle
    0.87
    iza
    0.87
     Niño
    0.86
    azy
    0.85
    mont
    0.85
     Paso
    0.84
    Activations Density 0.008%

    No Known Activations