© 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. 10-RES-JB
    11. 4622
    Prev
    Next
    INDEX
    Explanations

    political terms and entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various groups or roles within societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à
    -0.65
    ̶
    -0.60
    frog
    -0.60
    mone
    -0.59
    Ore
    -0.58
    lished
    -0.58
    Minecraft
    -0.57
    rss
    -0.57
    Jess
    -0.56
    abilia
    -0.53
    POSITIVE LOGITS
    '
    1.13
     themselves
    1.09
     are
    1.03
     aren
    1.00
    ']
    0.99
     prefer
    0.86
     ARE
    0.85
     feel
    0.85
     differ
    0.84
     comprise
    0.83
    Activations Density 0.312%

    No Known Activations