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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 14477
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'latitude'

    oai_token-act-pair · gpt-3.5-turbo

    words related to measurement and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.96
    afe
    -0.79
    IED
    -0.77
    haus
    -0.72
    oly
    -0.72
    en
    -0.72
    Bytes
    -0.71
    colo
    -0.70
    ublic
    -0.69
    bos
    -0.69
    POSITIVE LOGITS
     latitude
    0.98
    itudinal
    0.94
     Scotia
    0.77
    itud
    0.76
     carrot
    0.74
     Tackle
    0.68
     livest
    0.66
     Macron
    0.65
     Highlands
    0.65
     carrots
    0.64
    Activations Density 0.021%

    No Known Activations