© 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. 4-RES-JB
    11. 14834
    Prev
    Next
    INDEX
    Explanations

    locations, specifically cities and provinces

    oai_token-act-pair · gpt-3.5-turbo

    references to the province of Ontario

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

    No Comments

    Negative Logits
    ãģĦ
    -0.95
    ãĥ¼ãĥĨ
    -0.80
    ãĥ¬
    -0.74
     [+
    -0.73
    ãĥ¯
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
     CVE
    -0.68
    ãĤ§
    -0.67
    ãĥį
    -0.66
    BILITIES
    -0.66
    POSITIVE LOGITS
    ario
    1.20
    rack
    1.02
    ological
    0.98
    omet
    0.98
    arios
    0.96
    rue
    0.94
    ologically
    0.92
    reon
    0.89
    urst
    0.89
    rovers
    0.89
    Activations Density 0.009%

    No Known Activations