© 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. 24403
    Prev
    Next
    INDEX
    Explanations

    instances where something is "scrapped" or "renamed"

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts

    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
    wegian
    -0.75
    tain
    -0.72
    FIELD
    -0.69
    istani
    -0.68
    deck
    -0.67
     largeDownload
    -0.65
    anto
    -0.63
    CLASSIFIED
    -0.63
    lihood
    -0.63
    tains
    -0.63
    POSITIVE LOGITS
     favor
    1.81
     favour
    1.73
    effic
    1.22
    effect
    1.04
    activity
    0.99
    efficiency
    0.97
     disgust
    0.96
    wards
    0.95
    versions
    0.93
     haste
    0.93
    Activations Density 0.189%

    No Known Activations