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. 18448
    Prev
    Next
    INDEX
    Explanations

    percentages or statistical figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express statistical percentages or proportions

    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
    pedia
    -0.80
    ollah
    -0.74
    edin
    -0.70
     caching
    -0.68
    ebin
    -0.66
    unct
    -0.64
    idi
    -0.63
    hran
    -0.62
    alph
    -0.62
    dl
    -0.62
    POSITIVE LOGITS
     respondents
    0.89
    pees
    0.82
     households
    0.81
     GDP
    0.80
     surveyed
    0.73
     applicants
    0.71
     voters
    0.66
     variance
    0.66
     Fortune
    0.66
    âķIJ
    0.66
    Activations Density 0.071%

    No Known Activations