© 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. 8-RES-JB
    11. 19331
    Prev
    Next
    INDEX
    Explanations

    instances of connecting phrases like 'and'

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions that suggest a list or continuation of ideas

    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
    atan
    -0.78
    emi
    -0.75
     Powered
    -0.72
    DX
    -0.71
    busters
    -0.69
    spect
    -0.69
    BuyableInstoreAndOnline
    -0.68
    uta
    -0.68
    ibble
    -0.68
    ahime
    -0.67
    POSITIVE LOGITS
     consequently
    1.54
     furthermore
    1.50
     thus
    1.39
     hence
    1.37
     moreover
    1.35
     therefore
    1.30
     thereby
    1.26
     vice
    1.25
     secondly
    1.17
     thence
    1.16
    Activations Density 0.240%

    No Known Activations