© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12455
    Prev
    Next
    INDEX
    Explanations

    mentions or references to specific geographical locations, particularly Tamil Nadu and Chennai

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tamil language and the regions of Tamil Nadu and Kerala

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

    No Comments

    Negative Logits
    Ĺ
    -0.75
    inances
    -0.72
    hammad
    -0.71
    hl
    -0.71
    osit
    -0.71
    unin
    -0.70
    berman
    -0.70
    rd
    -0.69
    riet
    -0.68
    ĻĤ
    -0.67
    POSITIVE LOGITS
     Nadu
    1.77
     Tamil
    0.78
    nia
    0.77
     Pradesh
    0.76
     Gardens
    0.74
    ople
    0.70
     Baal
    0.70
     Herald
    0.69
    axis
    0.67
    orie
    0.67
    Activations Density 0.010%

    No Known Activations