© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10269
    Prev
    Next
    INDEX
    Explanations

    locations or directions with cardinal or ordinal directions such as north, northeast, west, etc

    oai_token-act-pair · gpt-3.5-turbo

    directions and geographical locations

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

    No Comments

    Negative Logits
    Os
    -0.69
    aughs
    -0.67
    ucha
    -0.64
    Tea
    -0.63
    ANS
    -0.63
     tainted
    -0.62
    BuyableInstoreAndOnline
    -0.62
    Fans
    -0.62
     Flavoring
    -0.62
    Released
    -0.62
    POSITIVE LOGITS
    wards
    1.10
    ward
    1.10
    itudinal
    1.06
     latitude
    1.03
    west
    0.91
    dimension
    0.90
    western
    0.87
     circumference
    0.85
     axis
    0.85
    outheast
    0.85
    Activations Density 0.113%

    No Known Activations