Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3327
    Prev
    Next
    INDEX
    Explanations

    names and words related to a person named Raj

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Raj

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĩãĤ£
    -0.73
    ãĤ¦
    -0.73
    POS
    -0.71
     Yankee
    -0.68
    éļ
    -0.68
    âϦ
    -0.67
    tein
    -0.67
    çĦ
    -0.64
    ä¹ĭ
    -0.62
    ãĤ¤
    -0.62
    POSITIVE LOGITS
    arat
    1.13
    aram
    0.92
    endra
    0.90
    alla
    0.87
    aji
    0.86
     Raj
    0.86
    ournal
    0.86
    uling
    0.85
    cliffe
    0.85
    ataka
    0.83
    Activations Density 0.015%

    No Known Activations