© 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. 4-RES-JB
    11. 10607
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving exponentials

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and terms related to dissolution and legal matters

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

    No Comments

    Negative Logits
    ebus
    -0.79
    akable
    -0.72
    urized
    -0.70
    sburg
    -0.70
    acco
    -0.70
    INGS
    -0.70
    ares
    -0.68
    asp
    -0.67
     BaseType
    -0.67
     ARTICLE
    -0.67
    POSITIVE LOGITS
    etheless
    1.05
    interstitial
    0.96
    swer
    0.84
    _{
    0.80
    omore
    0.80
    plet
    0.78
    etermination
    0.74
    onymous
    0.73
    ^{
    0.72
    ition
    0.71
    Activations Density 0.017%

    No Known Activations