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. 10-RES-JB
    6. 1854
    Prev
    Next
    INDEX
    Explanations

    names or words that end with 'ra' or 'raja'

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of 'ra', potentially referring to a specific character, theme, or focus in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regor
    -0.70
     Revel
    -0.65
    agascar
    -0.64
    mate
    -0.61
     unpop
    -0.61
    icians
    -0.60
     Polk
    -0.58
    ician
    -0.57
    TY
    -0.56
    orem
    -0.56
    POSITIVE LOGITS
    irie
    1.50
    fter
    1.37
    eus
    1.35
    fters
    1.31
    zzo
    1.23
    ppa
    1.21
    ppy
    1.20
    plets
    1.17
    ffe
    1.15
    ffiti
    1.14
    Activations Density 0.036%

    No Known Activations