© 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. 23575
    Prev
    Next
    INDEX
    Explanations

    numbers related to prices or rates

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and measurements related to costs and quantities

    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
    irtual
    -0.77
    laus
    -0.69
    uther
    -0.68
    ydia
    -0.66
    yang
    -0.65
    rawled
    -0.64
    ciplinary
    -0.61
    yz
    -0.61
    ictions
    -0.61
    opic
    -0.59
    POSITIVE LOGITS
     increments
    0.74
    riors
    0.72
     attRot
    0.69
     EPS
    0.67
    ²
    0.64
     plus
    0.63
     lease
    0.62
     Barg
    0.62
     blues
    0.61
    guide
    0.60
    Activations Density 0.017%

    No Known Activations