© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1160
    Prev
    Next
    INDEX
    Explanations

    relevant details regarding events, such as dates, locations, and actions performed

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to medical conditions and fatalities

    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
    erity
    -0.62
    theless
    -0.52
    enance
    -0.50
     coffers
    -0.49
     tyres
    -0.48
     feats
    -0.48
    sheets
    -0.48
     disadvantages
    -0.46
     outweigh
    -0.45
     Journals
    -0.45
    POSITIVE LOGITS
    ---------
    0.49
     [[
    0.46
     Oklahoma
    0.43
    ople
    0.42
    ÃĤ
    0.41
     Kansas
    0.41
    umm
    0.40
     basic
    0.40
     Maine
    0.39
     Alabama
    0.38
    Activations Density 0.463%

    No Known Activations