© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 10326
    Prev
    Next
    INDEX
    Explanations

    mentions of specific time periods or events

    oai_token-act-pair · gpt-3.5-turbo

    key topics related to current events and newsworthy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereafter
    -0.57
     successors
    -0.53
    Secondly
    -0.49
     present
    -0.48
    sic
    -0.48
     dotted
    -0.47
    }.
    -0.47
     thereafter
    -0.46
     preceding
    -0.46
    âĹ¼
    -0.46
    POSITIVE LOGITS
     âĢº
    0.75
    VIDIA
    0.71
    ccording
    0.66
    terness
    0.65
    ĵĺ
    0.62
    PDATE
    0.62
    maxwell
    0.60
     Calculator
    0.57
    pedia
    0.57
    atform
    0.57
    Activations Density 2.386%

    No Known Activations