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. 21992
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and sentencing

    oai_token-act-pair · gpt-3.5-turbo

    specific dates, events, or identifiers related to certain occurrences

    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
     )]
    -0.59
     ``
    -0.59
     ''
    -0.57
     .)
    -0.56
     EVs
    -0.54
    SPONSORED
    -0.54
    "],"
    -0.53
     Mubarak
    -0.52
    ...)
    -0.52
     Snapchat
    -0.50
    POSITIVE LOGITS
    resa
    0.93
    dinand
    0.93
    ptoms
    0.91
    otine
    0.90
    aples
    0.90
    etheless
    0.88
    jamin
    0.85
    agascar
    0.85
    odore
    0.84
    leneck
    0.81
    Activations Density 0.396%

    No Known Activations