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

    Neuronpedia

    Jacobian LensNEW
    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. 16615
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the speed or intensity of an action

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating speed or intensity of actions

    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
    tein
    -0.77
    ht
    -0.65
    cknowled
    -0.65
    bey
    -0.64
    hler
    -0.63
    overed
    -0.62
    vous
    -0.61
    ym
    -0.60
    izoph
    -0.59
    ean
    -0.59
    POSITIVE LOGITS
    },{"
    0.80
    aneously
    0.75
    utics
    0.75
     because
    0.74
     srfAttach
    0.73
     downstream
    0.71
     afterward
    0.70
     afterwards
    0.70
     consecut
    0.69
     throughout
    0.69
    Activations Density 0.410%

    No Known Activations