© 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. 9-RES-JB
    11. 20811
    Prev
    Next
    INDEX
    Explanations

    character names from a story

    oai_token-act-pair · gpt-3.5-turbo

    the character name "Weiss" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
    olphins
    -0.76
     NTS
    -0.67
     Palest
    -0.66
    indal
    -0.62
    actionDate
    -0.61
    cffffcc
    -0.60
     disse
    -0.60
     Babylon
    -0.60
     Flavoring
    -0.59
    POSITIVE LOGITS
     gigg
    1.16
     Weasley
    1.15
     smiled
    1.11
     frowned
    1.06
     frown
    1.06
     stared
    1.05
     sighed
    1.02
     glared
    1.01
     grinned
    1.01
     smir
    0.99
    Activations Density 0.127%

    No Known Activations