© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3315
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to various organizations or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to various acronyms and their definitions

    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
     HG
    -0.78
     lull
    -0.77
     skew
    -0.76
     jars
    -0.74
     hatch
    -0.74
     nests
    -0.74
     ig
    -0.71
     dragons
    -0.70
     gum
    -0.69
     lav
    -0.69
    POSITIVE LOGITS
    Advanced
    1.22
    Secure
    1.20
    short
    1.20
    pron
    1.19
    International
    1.13
    formerly
    1.10
    Independent
    1.07
    Virtual
    1.06
    National
    1.06
    Physical
    1.06
    Activations Density 0.065%

    No Known Activations