© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    political statements with a strong opinion

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters that signify significant content or themes

    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
     zoning
    -0.80
     territ
    -0.79
     plat
    -0.77
     hemor
    -0.77
     Borough
    -0.70
     Marketable
    -0.70
     destro
    -0.68
     charm
    -0.67
     habit
    -0.67
     dust
    -0.66
    POSITIVE LOGITS
    ¹
    1.15
    ª
    1.13
    ¸
    1.06
    ı
    1.04
    «
    0.99
    taboola
    0.97
    ¾
    0.96
    º
    0.94
    ³
    0.94
    ¦
    0.94
    Activations Density 0.063%

    No Known Activations