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. 0-RES-JB
    6. 8761
    Prev
    Next
    INDEX
    Explanations

    words related to the proper noun "Rojava", which could be a name or a location

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Ro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umen
    -0.77
     srfN
    -0.70
    ilateral
    -0.69
    sers
    -0.69
    lectic
    -0.68
     instr
    -0.64
    atever
    -0.62
    mer
    -0.60
     antibody
    -0.60
    graph
    -0.60
    POSITIVE LOGITS
     Ro
    3.84
    Ro
    2.78
     ro
    1.59
     roast
    1.52
     RO
    1.41
     Rooney
    1.33
     Rover
    1.26
     roasted
    1.23
     Robo
    1.12
    RO
    1.09
    Activations Density 0.018%

    No Known Activations