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. 2120
    Prev
    Next
    INDEX
    Explanations

    proper acronyms related to research organizations and technologies

    oai_token-act-pair · gpt-3.5-turbo

    ubiquitous references to the acronym "RI."

    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
    forth
    -0.76
    wagon
    -0.76
    kinson
    -0.74
    terson
    -0.69
     delay
    -0.69
    nesium
    -0.69
    rules
    -0.69
    lein
    -0.68
    dayName
    -0.67
    icians
    -0.66
    POSITIVE LOGITS
    Äĩ
    0.96
    YA
    0.95
    KER
    0.93
    VEN
    0.92
    ving
    0.90
    ASON
    0.89
    ECA
    0.84
    estinal
    0.83
    BE
    0.83
    PS
    0.83
    Activations Density 0.014%

    No Known Activations