© 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. 4-RES-JB
    11. 7256
    Prev
    Next
    INDEX
    Explanations

    the names of individuals in official or leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    the word "the," indicating a focus on definite articles in the text

    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
    mania
    -0.70
    ubi
    -0.66
    anye
    -0.65
    worn
    -0.65
     masturb
    -0.64
    goers
    -0.62
     rehears
    -0.61
    aji
    -0.61
     disrespect
    -0.61
     nostalg
    -0.61
    POSITIVE LOGITS
     aforementioned
    0.99
     largest
    0.91
     same
    0.90
     highest
    0.88
     National
    0.88
     smallest
    0.86
     International
    0.86
     latter
    0.85
     United
    0.84
     Americas
    0.83
    Activations Density 0.388%

    No Known Activations