© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16588
    Prev
    Next
    INDEX
    Explanations

    patterns related to software or coding, including terms like "incremental mode," "refresh time," and version numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to software version updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Labor
    -0.90
     Administration
    -0.86
     Fisheries
    -0.86
     Government
    -0.86
     Banking
    -0.84
     Migration
    -0.83
     Budget
    -0.82
     Champions
    -0.82
     Ministers
    -0.81
     Engineering
    -0.81
    POSITIVE LOGITS
    nc
    1.40
    sb
    1.40
    sg
    1.39
    gt
    1.36
    dx
    1.35
    mc
    1.35
    john
    1.35
    sat
    1.34
    cv
    1.34
    aq
    1.34
    Activations Density 0.281%

    No Known Activations