© 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. 6-RES-JB
    6. 463
    Prev
    Next
    INDEX
    Explanations

    words related to political positions or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific chemical compound or group of compounds, particularly those containing "ben."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinnikuman
    -0.73
     Emmy
    -0.67
    mable
    -0.64
    DNA
    -0.64
    mson
    -0.63
    Reviewer
    -0.62
    matic
    -0.61
    DON
    -0.59
    RS
    -0.59
     IG
    -0.58
    POSITIVE LOGITS
    jamin
    1.49
    keley
    0.89
    heimer
    0.89
    thal
    0.88
    ghazi
    0.86
    furt
    0.82
    ect
    0.80
    itude
    0.78
    hard
    0.76
    ick
    0.76
    Activations Density 0.042%

    No Known Activations