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. 10-RES-JB
    6. 214
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is available or open for consideration or acquisition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating items or topics that are available for consideration or debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leigh
    -0.73
    raph
    -0.71
    urally
    -0.67
    ynes
    -0.66
    ILE
    -0.65
    ryu
    -0.64
    hiba
    -0.64
     Ahead
    -0.64
    ashtra
    -0.64
    ipl
    -0.63
    POSITIVE LOGITS
     grabs
    1.64
     sale
    1.25
     renewal
    1.04
     negotiation
    1.01
     consideration
    0.98
     inspection
    0.97
     adoption
    0.96
     auction
    0.93
     pasture
    0.91
     discussion
    0.90
    Activations Density 0.064%

    No Known Activations