© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    phrases related to numeric values being below or above certain thresholds

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature thresholds

    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
    BUG
    -0.69
    VPN
    -0.67
    Commerce
    -0.65
    NetMessage
    -0.65
    mail
    -0.63
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.61
     VIDE
    -0.60
    UID
    -0.60
    ãĤ¹ãĥĪ
    -0.60
    oga
    -0.59
    POSITIVE LOGITS
     expectations
    1.09
     normal
    1.02
     expectation
    0.95
    normal
    0.93
     parity
    0.91
     optimum
    0.88
     subsistence
    0.88
     baseline
    0.86
     norms
    0.84
     usual
    0.84
    Activations Density 0.124%

    No Known Activations