© 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. 7-RES-JB
    11. 18661
    Prev
    Next
    INDEX
    Explanations

    superlatives and rankings related to countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to the United States as a prominent global entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     descriptions
    -0.83
     motions
    -0.76
     presentations
    -0.76
     lashes
    -0.74
     drawings
    -0.74
     strokes
    -0.73
     tattoos
    -0.71
     prescriptions
    -0.69
     tricks
    -0.69
    tones
    -0.69
    POSITIVE LOGITS
     battleground
    0.92
    nexus
    0.88
     nation
    0.88
     solidly
    0.83
     powerhouse
    0.82
     pioneer
    0.81
     foremost
    0.81
     dominant
    0.78
     Silicon
    0.76
     premier
    0.76
    Activations Density 0.393%

    No Known Activations