© 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. 22922
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    email addresses and contact information

    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
     Enabled
    -0.83
     Thunderbolt
    -0.81
     Scheme
    -0.79
     Purpose
    -0.79
     Inspection
    -0.79
     Reconstruction
    -0.79
     Standing
    -0.77
     Passive
    -0.76
     Capture
    -0.75
     Finder
    -0.75
    POSITIVE LOGITS
    iverpool
    1.06
    aho
    1.01
    john
    0.98
    internet
    0.96
    avis
    0.95
    christ
    0.93
    hess
    0.92
    manuel
    0.91
    anie
    0.91
    td
    0.91
    Activations Density 0.224%

    No Known Activations