© 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. 10111
    Prev
    Next
    INDEX
    Explanations

    words related to news headlines and current events

    oai_token-act-pair · gpt-3.5-turbo

    references to incidents involving threats or security issues

    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
     realise
    -1.14
     realised
    -1.09
     learnt
    -0.98
     favourites
    -0.96
     analyse
    -0.94
     recognise
    -0.93
     emphas
    -0.90
     analys
    -0.85
     maths
    -0.85
    Britain
    -0.83
    POSITIVE LOGITS
     marijuana
    0.80
     opioid
    0.80
     Hurricane
    0.80
     Dakota
    0.79
     Zika
    0.79
     encamp
    0.78
     homeless
    0.77
     Homeless
    0.77
     eviction
    0.76
     BLM
    0.76
    Activations Density 1.339%

    No Known Activations