© 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. 8-RES-JB
    11. 2463
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or changes

    oai_token-act-pair · gpt-3.5-turbo

    recurrent mentions of the word "the" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.87
    atures
    -0.85
     exceeds
    -0.72
    rooms
    -0.71
    ients
    -0.71
    ago
    -0.70
     solves
    -0.69
    chairs
    -0.68
    rates
    -0.68
    eds
    -0.68
    POSITIVE LOGITS
     inability
    1.09
     emergence
    1.08
     tendency
    1.06
     absence
    1.05
     presence
    1.04
     notion
    1.02
     idea
    0.99
     sheer
    0.97
     realization
    0.97
     insistence
    0.97
    Activations Density 0.207%

    No Known Activations