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. 5018
    Prev
    Next
    INDEX
    Explanations

    conditions of interest, financial transactions, and political relationships related to wars in Iraq and Afghanistan

    oai_token-act-pair · gpt-3.5-turbo

    references to sports broadcasting and related technologies

    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
    glers
    -0.61
    stice
    -0.59
    arij
    -0.55
    oulos
    -0.51
    aroo
    -0.49
    iHUD
    -0.49
    hovah
    -0.47
    ichick
    -0.46
    urdue
    -0.45
     Vaugh
    -0.45
    POSITIVE LOGITS
    minecraft
    0.51
    renches
    0.50
    ModLoader
    0.44
    uments
    0.43
    ivo
    0.43
     Hood
    0.43
    76561
    0.42
    mic
    0.42
    ãĥĥãĤ¯
    0.42
    ãĤ¦ãĤ¹
    0.41
    Activations Density 1.415%

    No Known Activations