© 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. 7-RES-JB
    11. 23733
    Prev
    Next
    INDEX
    Explanations

    mentions of political initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to various initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oil
    -0.87
    ãĥĥãĥī
    -0.76
    mbuds
    -0.75
    parts
    -0.70
    oiler
    -0.70
    bane
    -0.70
    cats
    -0.69
    ummies
    -0.67
    rox
    -0.67
    avid
    -0.64
    POSITIVE LOGITS
     undertaken
    0.89
    ually
    0.84
    eers
    0.84
     spearheaded
    0.81
     effort
    0.81
     initiative
    0.80
     aimed
    0.78
     aiming
    0.78
     initiatives
    0.77
     endeavor
    0.73
    Activations Density 0.029%

    No Known Activations