© 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. 11-RES-JB
    11. 23122
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to importance, comparison, and depth

    oai_token-act-pair · gpt-3.5-turbo

    superlative phrases that indicate a high degree or importance

    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
    culosis
    -0.80
    osterone
    -0.79
    rition
    -0.76
    ãĤ®
    -0.74
     Beans
    -0.72
    luck
    -0.71
    cci
    -0.69
    inoa
    -0.68
    oop
    -0.68
    shots
    -0.68
    POSITIVE LOGITS
     profound
    1.41
     insidious
    1.32
     consequential
    1.23
     potent
    1.20
     fundamental
    1.20
     pervasive
    1.20
     important
    1.20
     precious
    1.19
     mundane
    1.17
     sacred
    1.14
    Activations Density 0.208%

    No Known Activations