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. 20881
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds with "cycl" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to specific chemical compounds and processes, along with concepts of standardization and sorting

    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
    erb
    -0.88
    aston
    -0.87
    Charge
    -0.77
    Accessory
    -0.76
    assy
    -0.75
    tsy
    -0.75
    asar
    -0.74
     Advocate
    -0.73
    nder
    -0.73
    rue
    -0.72
    POSITIVE LOGITS
     standardized
    1.94
     cycl
    1.89
     randomized
    1.78
     fixed
    1.40
     fixes
    1.34
     placebo
    1.32
     stabilized
    1.24
     cleaned
    1.23
     regulated
    1.22
     solved
    1.16
    Activations Density 0.030%

    No Known Activations