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. 5-RES-JB
    6. 307
    Prev
    Next
    INDEX
    Explanations

    terms related to file sharing and various sharing services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of sharing, particularly in digital and economic contexts

    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
    endez
    -0.74
    ural
    -0.71
    ichick
    -0.70
    paio
    -0.68
    ensen
    -0.68
    herty
    -0.66
    onso
    -0.65
    ī
    -0.65
    undai
    -0.65
    erald
    -0.64
    POSITIVE LOGITS
    hare
    0.93
    itarian
    0.82
    cro
    0.81
    sheets
    0.79
    holding
    0.78
    sharing
    0.77
    holder
    0.75
    holders
    0.75
    ystem
    0.73
    hip
    0.72
    Activations Density 0.021%

    No Known Activations