© 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. 7-RES-JB
    11. 21572
    Prev
    Next
    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signal dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.80
    anuts
    -0.68
    eers
    -0.65
    adem
    -0.63
    ĪĴ
    -0.63
     annex
    -0.62
     periphery
    -0.61
    pec
    -0.60
     eighteen
    -0.60
    ·
    -0.60
    POSITIVE LOGITS
     reads
    1.06
    said
    1.04
     said
    0.99
     says
    0.95
     recalled
    0.88
     recalls
    0.87
     joked
    0.84
     tweeted
    0.84
     wrote
    0.84
     exclaimed
    0.80
    Activations Density 0.083%

    No Known Activations