Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4452
    Prev
    Next
    INDEX
    Explanations

    interactions or conversational dialogue involving gestures or actions

    oai_token-act-pair · gpt-3.5-turbo

    dialogues or conversational exchanges between characters

    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
     depended
    -0.84
    Had
    -0.83
     amounted
    -0.80
     lacked
    -0.80
     mattered
    -0.79
    was
    -0.78
     existed
    -0.76
     differed
    -0.75
     outwe
    -0.74
     constituted
    -0.74
    POSITIVE LOGITS
     stares
    0.91
     exclaim
    0.90
     hangs
    0.89
     begs
    0.88
     begins
    0.87
     asks
    0.87
     announces
    0.86
     pops
    0.84
     greets
    0.83
     realizes
    0.83
    Activations Density 0.908%

    No Known Activations