© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21174
    Prev
    Next
    INDEX
    Explanations

    instances of words related to rates or speeds

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rates or measurements

    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
    roots
    -0.85
    æĦ
    -0.80
    selves
    -0.80
    æ³
    -0.79
     Aires
    -0.79
    wives
    -0.78
    nis
    -0.77
    ername
    -0.77
    redients
    -0.75
    iances
    -0.74
    POSITIVE LOGITS
     occurrence
    0.96
     incidence
    0.84
     decline
    0.79
     incarceration
    0.76
     progress
    0.76
     deterioration
    0.72
     attrition
    0.70
     precipitation
    0.70
     interest
    0.70
     electricity
    0.70
    Activations Density 0.103%

    No Known Activations