© 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. 6-RES-JB
    11. 15252
    Prev
    Next
    INDEX
    Explanations

    phrases expressing admiration or support for something or someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fandom or support for various subjects

    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
    ammers
    -0.73
    eways
    -0.73
    estamp
    -0.68
    itars
    -0.68
    ©¶æ
    -0.68
    hem
    -0.68
    eworks
    -0.65
     coron
    -0.64
    ptoms
    -0.64
    uckles
    -0.64
    POSITIVE LOGITS
    lier
    0.88
    âĸ¬âĸ¬
    0.77
     à¨
    0.74
    cca
    0.74
     opener
    0.72
    atical
    0.71
     favorite
    0.69
    iable
    0.68
     inhibitor
    0.68
     favourite
    0.65
    Activations Density 0.145%

    No Known Activations