© 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. 4-RES-JB
    11. 22199
    Prev
    Next
    INDEX
    Explanations

    text surrounded by special characters in a repetitive pattern

    oai_token-act-pair · gpt-3.5-turbo

    titles or phrases related to expressions of dislike or hate

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

    No Comments

    Negative Logits
    hement
    -0.69
    nesday
    -0.61
     favoured
    -0.59
     honoured
    -0.58
     destro
    -0.56
     scrap
    -0.51
    uggest
    -0.50
     diseng
    -0.49
     favour
    -0.48
    ĸļ
    -0.48
    POSITIVE LOGITS
    Associated
    0.71
    ccording
    0.70
    ................................................................
    0.68
    ================================================================
    0.68
    ................................
    0.66
    --------------------------------------------------------
    0.65
    --------------------------------
    0.64
    ++++++++++++++++
    0.64
    OVER
    0.63
    Pand
    0.63
    Activations Density 0.560%

    No Known Activations