© 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. 24270
    Prev
    Next
    INDEX
    Explanations

    sentences describing how something functions or operates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "works" and its related usages in context

    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
    cele
    -0.72
     Ce
    -0.70
    SPONSORED
    -0.68
    antha
    -0.62
    Ey
    -0.62
    angular
    -0.61
    xual
    -0.61
    odder
    -0.61
    awn
    -0.61
    chal
    -0.61
    POSITIVE LOGITS
    paces
    1.32
    hops
    1.31
    heet
    1.29
    hift
    0.98
    hirt
    0.97
    pace
    0.95
    omething
    0.83
    icle
    0.81
    ometimes
    0.79
    bench
    0.79
    Activations Density 0.029%

    No Known Activations