© 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. 10-RES-JB
    11. 3014
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or places related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their living situations or fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inctions
    -0.88
    hemy
    -0.86
    Reviewer
    -0.83
     Cosponsors
    -0.83
    otin
    -0.80
    emis
    -0.78
     largeDownload
    -0.78
    apter
    -0.75
    ernels
    -0.75
    yss
    -0.73
    POSITIVE LOGITS
     apartment
    1.53
     bedroom
    1.38
     driveway
    1.36
     residence
    1.21
     rented
    1.18
     hotel
    1.17
     hometown
    1.16
     garage
    1.16
     backyard
    1.15
     mailbox
    1.15
    Activations Density 0.148%

    No Known Activations