© 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. 10-RES-JB
    11. 15988
    Prev
    Next
    INDEX
    Explanations

    numerical values as part of phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "Much" and phrases indicating quantity or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.72
    ħĭ
    -0.72
    pta
    -0.63
    slot
    -0.62
    oway
    -0.62
    opers
    -0.60
    pherd
    -0.60
    mediate
    -0.60
    ensis
    -0.59
    uble
    -0.59
    POSITIVE LOGITS
     happens
    1.22
     depends
    1.22
     happened
    1.07
     hinges
    0.99
     transpired
    0.97
     goes
    0.92
     depended
    0.91
     occurs
    0.90
     has
    0.83
     ensued
    0.81
    Activations Density 0.087%

    No Known Activations