© 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. 2-RES-JB
    11. 17158
    Prev
    Next
    INDEX
    Explanations

    words related to the city of Kolkata

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Kolkata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gemini
    -0.73
    ModLoader
    -0.72
     Schr
    -0.66
     tall
    -0.66
     exponential
    -0.63
    9999
    -0.63
     heav
    -0.61
     iT
    -0.61
     chi
    -0.60
     cz
    -0.58
    POSITIVE LOGITS
    olk
    1.21
    lore
    1.10
    estone
    1.06
    mere
    0.94
    vik
    0.90
    ovy
    0.89
    stad
    0.89
    stein
    0.87
    enthal
    0.86
    ita
    0.86
    Activations Density 0.006%

    No Known Activations