© 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. 10-RES-JB
    11. 11400
    Prev
    Next
    INDEX
    Explanations

    phrases expressing conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that begin with "If."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥŃ
    -0.70
    âĵĺ
    -0.68
    oves
    -0.67
    Ãį
    -0.66
    insula
    -0.64
    ãĥ³ãĤ¸
    -0.63
    iour
    -0.62
    akia
    -0.62
    number
    -0.62
    ggles
    -0.62
    POSITIVE LOGITS
     you
    1.17
     anything
    1.14
    fy
    1.03
     anyone
    0.95
     anybody
    0.94
     we
    0.83
     there
    0.82
     nothing
    0.81
     someone
    0.79
     somebody
    0.78
    Activations Density 0.101%

    No Known Activations