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. 20982
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological tools and applications

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of tools and applications that provide various functionalities

    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
     weakness
    -0.67
    Magikarp
    -0.67
     liking
    -0.66
    living
    -0.66
    UGH
    -0.63
    BIT
    -0.63
     falling
    -0.62
     anyway
    -0.62
     unpopular
    -0.61
     waning
    -0.61
    POSITIVE LOGITS
     allows
    1.29
     provides
    1.22
     enables
    1.21
     helps
    1.19
     summarizes
    1.16
     ensures
    1.13
     facilitates
    1.12
     teaches
    1.12
     collects
    1.10
     identifies
    1.10
    Activations Density 0.755%

    No Known Activations