© 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. 11-RES-JB
    11. 2645
    Prev
    Next
    INDEX
    Explanations

    political news and statements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and transitional phrases that indicate dialogue or reporting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.90
    atown
    -0.84
    ãĤ©
    -0.80
    Mods
    -0.77
    STD
    -0.72
    greg
    -0.71
    ãĥ¯ãĥ³
    -0.71
    Kids
    -0.71
    Ħ¢
    -0.70
    ãĥĺ
    -0.70
    POSITIVE LOGITS
     Foreign
    1.41
     Lavrov
    1.32
     diplomats
    1.26
     Defence
    1.21
     Deputy
    1.20
     Defense
    1.19
     Interior
    1.18
     Ambassador
    1.14
     Prime
    1.12
     Rouhani
    1.12
    Activations Density 0.241%

    No Known Activations