© 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. 10-RES-JB
    11. 5495
    Prev
    Next
    INDEX
    Explanations

    terms or phrases that are recognized or supported by a wide range of people or sources

    oai_token-act-pair · gpt-3.5-turbo

    the word "widely" and its variations in different contexts

    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
    hetics
    -0.71
    heny
    -0.68
    agate
    -0.68
    odan
    -0.65
    atics
    -0.64
    hetically
    -0.63
    xit
    -0.63
     Engineers
    -0.63
    door
    -0.62
    eki
    -0.62
    POSITIVE LOGITS
     regarded
    1.33
     viewed
    1.12
     acclaimed
    1.12
     circulated
    1.10
     publicized
    1.09
     accepted
    1.06
     praised
    1.05
     admired
    1.04
     considered
    1.04
     criticized
    1.02
    Activations Density 0.036%

    No Known Activations