© 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. 11-RES-JB
    11. 1108
    Prev
    Next
    INDEX
    Explanations

    countries or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.59
     understatement
    -0.58
    phies
    -0.56
     havoc
    -0.54
     needless
    -0.53
    brainer
    -0.53
    ktop
    -0.52
    ersion
    -0.52
    fortune
    -0.51
    recomm
    -0.51
    POSITIVE LOGITS
     and
    0.84
     factions
    0.81
     versus
    0.73
     sidx
    0.72
    arians
    0.67
     disparate
    0.63
     representatives
    0.63
    atana
    0.63
     AND
    0.63
     parties
    0.62
    Activations Density 0.168%

    No Known Activations