© 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. 9-RES-JB
    11. 9869
    Prev
    Next
    INDEX
    Explanations

    mentions of work, achievements, and accomplishments in various contexts such as sports, business, and military

    oai_token-act-pair · gpt-3.5-turbo

    mentions of job-related activities and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wikipedia
    -0.64
     realise
    -0.64
     WORLD
    -0.62
    Disclaimer
    -0.60
     coward
    -0.60
     HUGE
    -0.59
     Cthulhu
    -0.58
    ONDON
    -0.57
     Governments
    -0.57
     Rothschild
    -0.57
    POSITIVE LOGITS
    pection
    0.65
     deliveries
    0.64
     readings
    0.62
     inhal
    0.62
     infusion
    0.61
     inspections
    0.61
     workload
    0.60
     consultations
    0.60
     inspection
    0.60
     sessions
    0.59
    Activations Density 1.247%

    No Known Activations