© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 963
    Prev
    Next
    INDEX
    Explanations

    country names, specifically "Sierra Leone" and "El Salvador"

    oai_token-act-pair · gpt-4-turbo

    locations, specifically countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly countries

    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
    Hug
    -0.71
    amy
    -0.69
    onym
    -0.68
    Els
    -0.66
    ifice
    -0.66
     Merrill
    -0.63
    FACE
    -0.63
    Layer
    -0.61
    Jul
    -0.61
    TIT
    -0.60
    POSITIVE LOGITS
     Leone
    1.32
     Outbreak
    0.87
    istani
    0.84
    culosis
    0.84
     Liberia
    0.79
     Congo
    0.79
    vernment
    0.76
    istan
    0.75
    vati
    0.75
     Nadu
    0.74
    Activations Density 0.006%

    No Known Activations