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. 8-RES-JB
    6. 9692
    Prev
    Next
    INDEX
    Explanations

    words related to electronic communication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to email communication and digital interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouple
    -0.65
    ouf
    -0.64
    swer
    -0.61
     logo
    -0.60
     footprint
    -0.58
     Difference
    -0.57
    problem
    -0.57
     backdoor
    -0.56
    agame
    -0.56
     suite
    -0.56
    POSITIVE LOGITS
     proportions
    0.75
     circles
    0.69
    bugs
    0.68
    livion
    0.68
    speak
    0.67
     folklore
    0.65
    boarding
    0.62
     fame
    0.62
    arenthood
    0.62
     strangers
    0.61
    Activations Density 1.220%

    No Known Activations