© 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. 7-RES-JB
    11. 21808
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and groups involved in humanitarian issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TAMADRA
    -0.64
    uated
    -0.63
    bidden
    -0.63
     explan
    -0.60
     rewarded
    -0.60
     Peb
    -0.60
    200000
    -0.59
     Feast
    -0.59
    Houston
    -0.59
     Kurd
    -0.57
    POSITIVE LOGITS
    oub
    0.76
    lance
    0.75
    casters
    0.73
    wings
    0.72
    obs
    0.72
    resses
    0.71
    ashes
    0.70
    isine
    0.70
    ress
    0.69
    guards
    0.69
    Activations Density 0.431%

    No Known Activations