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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15787
    Prev
    Next
    INDEX
    Explanations

    proper names specifically mentioning "Raj"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 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
     fireplace
    -0.65
    ãĤ¦
    -0.64
    Favorite
    -0.60
     Sounders
    -0.58
     Wolves
    -0.57
     precisely
    -0.57
     AMERICA
    -0.57
     Myr
    -0.57
     Enterprise
    -0.56
     harbor
    -0.55
    POSITIVE LOGITS
    endra
    1.28
    arat
    1.22
    aram
    1.19
    rang
    1.06
    put
    1.03
    esh
    1.00
    deep
    0.99
    iage
    0.98
    hari
    0.96
    iv
    0.95
    Activations Density 0.032%

    No Known Activations