© 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. 6-RES-JB
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving a variety of items, such as notices, donations, and complaints

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "received" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fall
    -0.64
    hole
    -0.58
     coffin
    -0.57
    olini
    -0.57
     invari
    -0.56
     endeavor
    -0.55
    flation
    -0.54
    spir
    -0.54
     arteries
    -0.54
    apse
    -0.53
    POSITIVE LOGITS
    sbm
    0.82
    imental
    0.79
     permission
    0.78
     commissions
    0.76
    terson
    0.75
    DragonMagazine
    0.74
    å¼
    0.74
    ASED
    0.73
    andom
    0.73
    namese
    0.73
    Activations Density 0.053%

    No Known Activations