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. 11-RES-JB
    6. 3033
    Prev
    Next
    INDEX
    Explanations

    famous personalities and public figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various levels of achievement and recognition in the entertainment and sports industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illance
    -0.72
    potion
    -0.72
    iculty
    -0.68
    cffffcc
    -0.67
    ursed
    -0.67
    abus
    -0.67
    ject
    -0.66
    rection
    -0.65
    pmwiki
    -0.65
    amide
    -0.64
    POSITIVE LOGITS
     Quentin
    1.11
     Jonah
    1.05
     Cheryl
    1.05
     Nicola
    1.04
     Sidney
    1.02
     Sonny
    1.02
     Trey
    1.02
     Axel
    1.02
     Matthew
    1.02
     Alberto
    1.02
    Activations Density 0.342%

    No Known Activations