© 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. 7552
    Prev
    Next
    INDEX
    Explanations

    sentences indicating understanding or comprehension

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comprehension or understanding

    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
    DOWN
    -0.66
    mage
    -0.65
    aunder
    -0.64
    rouse
    -0.63
    izons
    -0.62
    artney
    -0.62
    patch
    -0.61
     psychiat
    -0.60
    ield
    -0.60
    onding
    -0.60
    POSITIVE LOGITS
     myself
    0.94
     Citation
    0.63
    ANA
    0.61
     firsthand
    0.60
     Kahn
    0.59
     count
    0.58
     reiterate
    0.58
    poke
    0.57
     regrets
    0.57
     exaggeration
    0.56
    Activations Density 0.371%

    No Known Activations