© 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. 10-RES-JB
    11. 6581
    Prev
    Next
    INDEX
    Explanations

    locations and place names

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.70
     acceler
    -0.69
     Swed
    -0.66
     Greenberg
    -0.64
     smoker
    -0.63
     Giov
    -0.62
     Cic
    -0.61
    Miller
    -0.60
     Wenger
    -0.60
     McCarthy
    -0.60
    POSITIVE LOGITS
     district
    1.10
     Pradesh
    1.09
    abad
    1.08
    ashtra
    1.08
    agar
    1.06
    pur
    1.01
    anga
    1.01
     township
    1.01
     Province
    0.99
    umbai
    0.99
    Activations Density 0.117%

    No Known Activations