© 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. 6-RES-JB
    11. 13616
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or nationalities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of countries, companies, and organizations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.70
    ////
    -0.63
     Emails
    -0.60
    ispers
    -0.59
     Sear
    -0.59
    immers
    -0.58
    Scroll
    -0.57
    âĶģ
    -0.57
    inse
    -0.57
     Guan
    -0.57
    POSITIVE LOGITS
    mates
    1.44
    mate
    1.27
     mates
    1.07
     mate
    0.87
    men
    0.79
    leader
    0.74
     colleague
    0.74
     counterparts
    0.74
    ÃŃs
    0.69
    atana
    0.66
    Activations Density 0.155%

    No Known Activations