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. 8-RES-JB
    6. 19862
    Prev
    Next
    INDEX
    Explanations

    proper names 'Raj' appearing in sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Raj."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.70
     precisely
    -0.64
     Heavenly
    -0.58
     transsexual
    -0.58
     Mississ
    -0.57
     Liberia
    -0.57
     paranormal
    -0.57
    ABLE
    -0.56
     glue
    -0.56
    ears
    -0.56
    POSITIVE LOGITS
    arat
    1.16
    oux
    0.95
    aram
    0.95
    assi
    0.92
    uling
    0.91
    rely
    0.91
    hari
    0.90
    cliffe
    0.89
    aic
    0.88
    onian
    0.88
    Activations Density 0.023%

    No Known Activations