© 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. 7812
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or location named "Che"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Che" and related entities or concepts

    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
     CTR
    -0.83
    ãĥ¼ãĥĨ
    -0.81
    ãĥ¼ãĥĨãĤ£
    -0.77
     Archdemon
    -0.69
     SPD
    -0.67
     executive
    -0.66
     Instruments
    -0.65
     Icelandic
    -0.64
     Curiosity
    -0.62
     numbering
    -0.60
    POSITIVE LOGITS
    bones
    1.18
    lean
    1.16
    hou
    1.13
    chet
    1.01
    esy
    0.99
    bag
    0.98
    anut
    0.97
    apeake
    0.96
    vette
    0.94
    bon
    0.93
    Activations Density 0.013%

    No Known Activations