© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8959
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "Washington"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Washington Post" and its relevance in the text

    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
    NetMessage
    -0.86
    avorite
    -0.81
    netflix
    -0.77
    merce
    -0.75
    thood
    -0.74
    roo
    -0.72
    gart
    -0.72
    wana
    -0.70
     beware
    -0.69
    duty
    -0.69
    POSITIVE LOGITS
     Observer
    1.08
     Times
    1.07
     Herald
    0.96
     Journal
    0.94
    Times
    0.91
     Institute
    0.91
     Tribune
    0.89
     Blade
    0.89
    Journal
    0.88
     Evening
    0.87
    Activations Density 0.115%

    No Known Activations