© 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. 11193
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or actions taking place in those locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and critical situations

    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
     Yorkers
    -0.58
     ticking
    -0.57
     relates
    -0.56
     mete
    -0.55
    quickShipAvailable
    -0.53
     misses
    -0.52
     extraord
    -0.52
     sqor
    -0.52
    ratulations
    -0.51
    Americans
    -0.50
    POSITIVE LOGITS
     premises
    0.83
     booth
    0.79
     kios
    0.77
     headquarters
    0.77
     courtyard
    0.77
     plantation
    0.75
     checkpoint
    0.75
     offices
    0.74
     courthouse
    0.74
    astery
    0.73
    Activations Density 1.173%

    No Known Activations