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. 12116
    Prev
    Next
    INDEX
    Explanations

    statistics and research findings

    oai_token-act-pair · gpt-3.5-turbo

    statistics regarding health and economic conditions

    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
    aban
    -0.77
    ~~~~
    -0.69
    iphate
    -0.67
    pless
    -0.66
    )?
    -0.64
    .--
    -0.64
    Vers
    -0.63
    });
    -0.63
    !/
    -0.62
    iky
    -0.62
    POSITIVE LOGITS
     median
    0.85
     average
    0.84
    Average
    0.80
    average
    0.78
     estimated
    0.76
     Nielsen
    0.73
     %
    0.72
     Average
    0.71
     statistically
    0.70
     percentage
    0.69
    Activations Density 0.769%

    No Known Activations