© 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. 7-RES-JB
    11. 24057
    Prev
    Next
    INDEX
    Explanations

    phrases relating to social or political movements or campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective identity and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >[
    -0.74
     veins
    -0.72
     peculiar
    -0.71
     apologies
    -0.67
    uitous
    -0.67
     folklore
    -0.64
    umerable
    -0.64
     chem
    -0.63
    ĸļ
    -0.63
    olver
    -0.63
    POSITIVE LOGITS
     Consent
    0.91
     Yourself
    0.91
     Own
    0.89
     Tomorrow
    0.89
     Funding
    0.88
     Slowly
    0.86
     Loud
    0.82
     Terrorism
    0.82
    ebook
    0.82
     Faster
    0.81
    Activations Density 0.318%

    No Known Activations