© 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. 582
    Prev
    Next
    INDEX
    Explanations

    adjectives related to stability and persistence

    oai_token-act-pair · gpt-3.5-turbo

    words related to staleness or stagnation in various contexts

    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
    ramid
    -0.77
    NetMessage
    -0.76
    hammad
    -0.75
     Nationwide
    -0.74
    yre
    -0.73
     Agency
    -0.72
    0100
    -0.71
    FU
    -0.69
     Simulator
    -0.69
     Loans
    -0.69
    POSITIVE LOGITS
    emate
    1.37
    wart
    1.30
    warts
    1.24
     stal
    1.19
    eness
    0.94
    ances
    0.86
    stal
    0.83
    staff
    0.79
    atial
    0.76
    thal
    0.75
    Activations Density 0.008%

    No Known Activations