© 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. 8-RES-JB
    11. 6977
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, ranks, and military units

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and governmental structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GET
    -0.66
    bats
    -0.65
     cloaked
    -0.62
    ctrl
    -0.59
     OTHER
    -0.59
    Feed
    -0.58
    opolis
    -0.58
     havens
    -0.58
    olini
    -0.58
    1920
    -0.57
    POSITIVE LOGITS
    imester
    0.99
    artment
    0.83
     onwards
    0.83
    endment
    0.82
    iece
    0.77
     anniversary
    0.75
    secut
    0.73
    alion
    0.72
    amic
    0.72
     Anniversary
    0.69
    Activations Density 0.193%

    No Known Activations