© 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 EvalsExportsinterp-engineNEWAPI 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. 24336
    Prev
    Next
    INDEX
    Explanations

    locations with words indicating local specificity

    oai_token-act-pair · gpt-3.5-turbo

    locations associated with people or organizations

    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
     replay
    -0.77
     indicators
    -0.75
     coefficient
    -0.74
     thumbs
    -0.73
     headlights
    -0.72
     "%
    -0.70
     elim
    -0.69
     revers
    -0.69
     criterion
    -0.69
     bip
    -0.69
    POSITIVE LOGITS
    based
    1.58
    area
    1.46
    centric
    1.27
    style
    1.22
    themed
    1.21
    sized
    1.15
    focused
    1.10
    derived
    1.07
    centered
    1.06
    bound
    1.06
    Activations Density 0.064%

    No Known Activations