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. 19876
    Prev
    Next
    INDEX
    Explanations

    terms related to website domains

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dot" and its variations

    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
    CVE
    -0.72
    IENCE
    -0.67
    FUL
    -0.66
    ANS
    -0.66
     HELP
    -0.66
    idential
    -0.65
     Referred
    -0.63
     Belief
    -0.62
    itable
    -0.62
    Demand
    -0.61
    POSITIVE LOGITS
    dot
    1.29
     dot
    0.92
    uate
    0.91
    eret
    0.85
    ching
    0.83
    olor
    0.79
    rix
    0.79
    oday
    0.78
    ched
    0.77
    biz
    0.77
    Activations Density 0.013%

    No Known Activations