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. 1087
    Prev
    Next
    INDEX
    Explanations

    references to historical events and time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient historical periods and dates

    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
    cipled
    -0.90
    NESS
    -0.77
     Ally
    -0.77
     hurting
    -0.74
     VMware
    -0.73
     Comcast
    -0.73
     Blaster
    -0.72
     Tonight
    -0.69
    committee
    -0.69
     hurts
    -0.69
    POSITIVE LOGITS
     Archae
    1.20
     archae
    1.14
     Egyptians
    1.13
    Ancient
    1.11
     civilisation
    1.10
     civilizations
    1.09
     archaeological
    1.09
     ancestor
    1.08
     Antiqu
    1.08
     Zoro
    1.07
    Activations Density 0.849%

    No Known Activations