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. 9-RES-JB
    6. 654
    Prev
    Next
    INDEX
    Explanations

    phrases related to advice or steps to take

    oai_token-act-pair · gpt-3.5-turbo

    advice related to purchasing decisions or precautions to take when buying something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Democr
    -0.73
    hawks
    -0.73
     )]
    -0.73
    "},
    -0.70
    Streamer
    -0.69
    ĸļ
    -0.66
    twitter
    -0.64
    hai
    -0.63
    apo
    -0.62
    Translation
    -0.60
    POSITIVE LOGITS
     yourself
    1.37
     yourselves
    1.08
     your
    1.04
    your
    1.02
     Yourself
    1.00
     YOUR
    0.93
    Your
    0.91
     confidently
    0.89
     yours
    0.87
     Your
    0.87
    Activations Density 0.737%

    No Known Activations