© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17857
    Prev
    Next
    INDEX
    Explanations

    the word "Congo" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Cong" and "Congo."

    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
    IPS
    -0.80
     Gleaming
    -0.76
    OHN
    -0.75
     Marketable
    -0.74
     Leilan
    -0.73
    BALL
    -0.69
     Fields
    -0.68
     SPORTS
    -0.67
    ãĤ´ãĥ³
    -0.66
    ARM
    -0.65
    POSITIVE LOGITS
    regation
    1.16
    regate
    1.11
    rats
    1.06
    ressive
    1.02
     Cong
    1.02
    cong
    1.02
    ression
    0.95
    reg
    0.92
    rates
    0.87
    office
    0.87
    Activations Density 0.022%

    No Known Activations