© 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. 8-RES-JB
    11. 10923
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving writing notes and locking doors

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vulner
    -0.68
    mund
    -0.65
    leground
    -0.63
    arial
    -0.59
    aneers
    -0.58
    Split
    -0.57
    è¦
    -0.56
    buster
    -0.56
    raham
    -0.55
    Tracker
    -0.53
    POSITIVE LOGITS
     extent
    1.00
    merce
    0.71
     detriment
    0.65
     whence
    0.63
    Ĥİ
    0.62
     fullest
    0.61
    £ı
    0.60
    displayText
    0.59
     tune
    0.59
     foregoing
    0.58
    Activations Density 0.049%

    No Known Activations