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. 10-RES-JB
    6. 17202
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location named "our"

    oai_token-act-pair · gpt-3.5-turbo

    the word "our."

    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
     steroids
    -0.69
    ulator
    -0.67
    aeda
    -0.65
    ulators
    -0.64
     Robo
    -0.62
     buckle
    -0.62
     release
    -0.60
     Rasmussen
    -0.59
     steroid
    -0.58
     electronically
    -0.57
    POSITIVE LOGITS
    dain
    1.44
    neau
    1.34
    neys
    1.12
    dan
    1.04
    ishment
    0.99
    tesy
    0.96
    din
    0.95
    nee
    0.92
    inho
    0.92
    ished
    0.91
    Activations Density 0.026%

    No Known Activations