Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3725
    Prev
    Next
    INDEX
    Explanations

    medical terms related to hormones and drug substances, including specific brand names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychoactive substances and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rouge
    -0.80
     Pens
    -0.70
     Jeep
    -0.67
     Outbreak
    -0.64
    ãĥ¯
    -0.63
    MET
    -0.63
     Company
    -0.63
    COL
    -0.61
     Griffin
    -0.59
     MLA
    -0.59
    POSITIVE LOGITS
    otropic
    3.36
    otrop
    2.86
    vell
    1.99
    utive
    1.14
    ologically
    1.08
    Known
    0.97
    Balt
    0.91
     Trap
    0.89
    areth
    0.85
    rophic
    0.85
    Activations Density 0.050%

    No Known Activations