© 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. 6877
    Prev
    Next
    INDEX
    Explanations

    actions or capabilities related to interaction or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and auxiliary verbs indicating capability or obligation

    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
     pupil
    -0.65
    2020
    -0.65
     predecessor
    -0.65
     majesty
    -0.64
    Quantity
    -0.62
    Shadow
    -0.62
     magnification
    -0.61
    Ur
    -0.60
     successor
    -0.60
    ixties
    -0.59
    POSITIVE LOGITS
     routinely
    0.87
    ateurs
    0.78
     beware
    0.75
     understandably
    0.66
     everywhere
    0.65
     alike
    0.65
     always
    0.64
     ALWAYS
    0.63
     generally
    0.61
     Cath
    0.61
    Activations Density 0.861%

    No Known Activations