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. 4-RES-JB
    6. 12745
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds or medications

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with specific chemical compounds or related scientific terminology

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

    No Comments

    Negative Logits
     Shattered
    -0.81
    Oracle
    -0.71
    faced
    -0.68
    print
    -0.67
    URN
    -0.66
    POS
    -0.65
     Gadget
    -0.65
     LCS
    -0.64
     Mavericks
    -0.64
     Resolution
    -0.63
    POSITIVE LOGITS
    ipop
    1.21
    ateral
    1.07
    ombo
    1.07
    ength
    1.06
     destro
    1.06
    ossus
    1.02
    idge
    0.99
    ingu
    0.97
    iberal
    0.97
    ice
    0.96
    Activations Density 0.008%

    No Known Activations