© 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. 17236
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of charts or graphs

    oai_token-act-pair · gpt-3.5-turbo

    references to charts and graphical data representations

    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
    ntil
    -0.71
     throats
    -0.70
     Romeo
    -0.69
    INGTON
    -0.67
    Interstitial
    -0.66
    ignt
    -0.66
    vae
    -0.64
    IRE
    -0.61
    ternity
    -0.60
    ITY
    -0.60
    POSITIVE LOGITS
    ered
    1.15
    chart
    0.98
    ued
    0.92
     charts
    0.86
     Chart
    0.81
     chart
    0.79
    ographer
    0.78
    eer
    0.75
    maker
    0.74
    ically
    0.73
    Activations Density 0.039%

    No Known Activations