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. 9-RES-JB
    6. 21077
    Prev
    Next
    INDEX
    Explanations

    phrases related to nutritional information and components

    oai_token-act-pair · gpt-3.5-turbo

    compound phrases or terms related to composition and qualities, particularly focusing on nitrogen and oxygen content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Views
    -0.70
     Persons
    -0.67
     Elections
    -0.66
     Chiefs
    -0.66
     exceptions
    -0.66
     Quincy
    -0.65
    ulhu
    -0.65
     Vaughn
    -0.65
     execut
    -0.65
     Patron
    -0.65
    POSITIVE LOGITS
    producing
    1.46
    filled
    1.34
    fuel
    1.31
    containing
    1.30
    covered
    1.30
    laden
    1.29
    rich
    1.29
    induced
    1.28
    driven
    1.27
    based
    1.25
    Activations Density 0.078%

    No Known Activations