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. 6755
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emotional attachment or affection

    oai_token-act-pair · gpt-3.5-turbo

    intense expressions of strong emotional attachment or feelings

    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
    auri
    -0.72
     rewritten
    -0.70
    gged
    -0.66
    itialized
    -0.65
    itta
    -0.65
     plur
    -0.64
    Explore
    -0.61
    pload
    -0.61
    yrim
    -0.60
    nings
    -0.59
    POSITIVE LOGITS
    âĺ
    0.80
    today
    0.69
    dies
    0.67
    âĻ¥
    0.64
    Tex
    0.64
    heartedly
    0.64
    handedly
    0.64
    actively
    0.63
    ãĤ§
    0.62
     ðŁĺ
    0.62
    Activations Density 0.218%

    No Known Activations