© 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. 0-RES-JB
    11. 7532
    Prev
    Next
    INDEX
    Explanations

    informal or colloquial references to things or items

    oai_token-act-pair · gpt-3.5-turbo

    generic references to various types of content or items referred to as "stuff."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Figure
    -0.65
    severe
    -0.62
    strong
    -0.61
    ural
    -0.61
    uo
    -0.59
    significant
    -0.59
    zai
    -0.58
    ¹
    -0.58
     located
    -0.58
     pursuant
    -0.57
    POSITIVE LOGITS
     stuff
    3.71
    stuff
    2.36
     Stuff
    2.23
     shit
    2.06
     crap
    2.04
     things
    1.59
     goodies
    1.41
     bullshit
    1.39
     thing
    1.34
     guy
    1.25
    Activations Density 0.012%

    No Known Activations