Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 24525
    Prev
    Next
    INDEX
    Explanations

    phrases related to office furniture or items typically found on a desk

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "desk."

    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
    actionDate
    -0.90
    Interstitial
    -0.88
     Adin
    -0.83
    Ô
    -0.82
    6666
    -0.72
     Adren
    -0.68
    ICO
    -0.67
    ICAN
    -0.67
     ESC
    -0.66
    ETH
    -0.65
    POSITIVE LOGITS
    tops
    1.78
     drawer
    1.20
    top
    1.06
     Desk
    1.00
     desk
    0.97
    chair
    0.90
    lift
    0.86
    pointer
    0.85
    Desk
    0.80
     desks
    0.80
    Activations Density 0.017%

    No Known Activations