© 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. 23650
    Prev
    Next
    INDEX
    Explanations

    wording related to opt-in promotions or advertisements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to promotional content, offers, and updates

    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
    closed
    -0.71
    mand
    -0.69
    lly
    -0.69
    urally
    -0.68
    geist
    -0.67
    Registered
    -0.64
    ograp
    -0.62
    stood
    -0.60
     Kamp
    -0.60
    agate
    -0.59
    POSITIVE LOGITS
    ctory
    0.83
    pring
    0.80
     occasional
    0.78
    ource
    0.72
     Schwarzenegger
    0.70
    piracy
    0.69
    poons
    0.67
    Subscribe
    0.67
    hips
    0.65
    ause
    0.64
    Activations Density 0.020%

    No Known Activations