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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 12750
    Prev
    Next
    INDEX
    Explanations

    URLs of specific websites

    oai_token-act-pair · gpt-3.5-turbo

    references to web domains and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bour
    -0.75
     shedding
    -0.70
     behavi
    -0.69
     streng
    -0.68
     affirm
    -0.68
     rhy
    -0.64
     superst
    -0.61
    attled
    -0.60
     represented
    -0.60
     grounding
    -0.60
    POSITIVE LOGITS
    76561
    0.87
    vic
    0.83
    wordpress
    0.83
    mil
    0.83
    bean
    0.81
    edu
    0.77
    dk
    0.77
    yahoo
    0.77
    android
    0.76
    cell
    0.76
    Activations Density 0.093%

    No Known Activations