© 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. 8-RES-JB
    11. 3868
    Prev
    Next
    INDEX
    Explanations

    personal identification information like names and addresses

    oai_token-act-pair · gpt-3.5-turbo

    details related to personal identification and information submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lude
    -0.71
    anship
    -0.70
    gers
    -0.69
    chemy
    -0.68
    odynam
    -0.68
    humans
    -0.68
    uba
    -0.67
    inho
    -0.67
    Wan
    -0.67
    knit
    -0.66
    POSITIVE LOGITS
     initials
    1.06
     nearest
    0.94
     invoice
    0.85
     username
    0.84
     number
    0.80
     name
    0.79
     desired
    0.76
     URL
    0.76
     receipt
    0.75
     postal
    0.75
    Activations Density 0.373%

    No Known Activations