© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5170
    Prev
    Next
    INDEX
    Explanations

    modifiers and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of casual conversation or transitions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.75
    è¦ļéĨĴ
    -0.71
    natureconservancy
    -0.68
    reated
    -0.66
    à¨
    -0.65
    nai
    -0.65
    angering
    -0.64
    externalActionCode
    -0.64
    ngth
    -0.62
    Pokémon
    -0.61
    POSITIVE LOGITS
     bye
    0.84
    bye
    0.77
     Wrong
    0.75
     congratulations
    0.69
     yeah
    0.66
     Sorry
    0.65
    yeah
    0.65
     goodbye
    0.65
     maybe
    0.65
     excuse
    0.64
    Activations Density 0.051%

    No Known Activations