© 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. 6298
    Prev
    Next
    INDEX
    Explanations

    words related to growth and progress

    oai_token-act-pair · gpt-3.5-turbo

    connections between different concepts or entities

    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
    ttes
    -0.72
    oning
    -0.71
    WARNING
    -0.71
    TF
    -0.71
     Guilty
    -0.68
     Baseball
    -0.67
    Newsletter
    -0.67
    tf
    -0.65
     Logged
    -0.64
    ML
    -0.64
    POSITIVE LOGITS
     flourish
    1.10
     prosper
    1.09
     decay
    1.08
     thrive
    0.99
     evolve
    0.97
     deepen
    0.94
     innovate
    0.91
     metast
    0.86
     expand
    0.85
     stabilize
    0.84
    Activations Density 0.203%

    No Known Activations