© 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. 8560
    Prev
    Next
    INDEX
    Explanations

    keywords related to cyber attacks and server issues

    oai_token-act-pair · gpt-3.5-turbo

    references to internet server issues and disruptions

    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
    bent
    -0.79
    quart
    -0.77
     envision
    -0.75
     Nobel
    -0.73
    Environmental
    -0.70
    },{"
    -0.70
     molded
    -0.70
     Oral
    -0.69
    Narr
    -0.69
    chem
    -0.66
    POSITIVE LOGITS
     outage
    1.46
     HTTPS
    1.38
     servers
    1.36
     login
    1.28
     iCloud
    1.25
     URLs
    1.23
     users
    1.21
     DMCA
    1.19
     cached
    1.19
     offline
    1.17
    Activations Density 0.509%

    No Known Activations