© 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. 8-RES-JB
    11. 3192
    Prev
    Next
    INDEX
    Explanations

    pairs of phrases linked by semicolons or parentheses

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and conjunctions, particularly in contexts involving lists and complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "!
    -0.76
    ospace
    -0.70
    trak
    -0.68
    lez
    -0.67
    ":"/
    -0.66
    nant
    -0.65
     Hatt
    -0.63
    udos
    -0.63
     dstg
    -0.62
    okane
    -0.62
    POSITIVE LOGITS
     secondly
    1.50
     Secondly
    1.43
    Secondly
    1.07
     Second
    0.88
     ();
    0.75
    âĢ¢
    0.71
     Also
    0.68
     –
    0.67
     âĩ
    0.64
     Ideally
    0.64
    Activations Density 0.582%

    No Known Activations