© 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. 2-RES-JB
    11. 12524
    Prev
    Next
    INDEX
    Explanations

    words related to nationalization or processes involving converting private assets into public ownership

    oai_token-act-pair · gpt-3.5-turbo

    words related to processes of categorization or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loo
    -0.73
    agher
    -0.69
    ood
    -0.65
    atta
    -0.63
    ajo
    -0.60
    bie
    -0.59
    aders
    -0.57
     Clare
    -0.57
     boun
    -0.57
    idian
    -0.57
    POSITIVE LOGITS
    ize
    0.84
    Sov
    0.76
    ized
    0.70
    Magikarp
    0.70
    IZE
    0.69
    eer
    0.66
    urdue
    0.66
    imize
    0.65
    ated
    0.65
    ablishment
    0.63
    Activations Density 0.047%

    No Known Activations