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. 16087
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and interactions between people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships and social 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
    Scroll
    -0.68
     decl
    -0.66
     graphic
    -0.66
    Attempt
    -0.62
     spect
    -0.61
     parsing
    -0.61
     recount
    -0.61
     leveling
    -0.60
     Graphic
    -0.60
     WATCHED
    -0.59
    POSITIVE LOGITS
     him
    1.07
    everyone
    0.98
     everybody
    0.95
    him
    0.94
     myself
    0.93
     anybody
    0.92
    them
    0.92
     HIM
    0.91
     theirs
    0.89
     somebody
    0.87
    Activations Density 0.574%

    No Known Activations