© 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. 1-RES-JB
    11. 5266
    Prev
    Next
    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.52
    nces
    -0.52
    xon
    -0.52
     largeDownload
    -0.50
    akening
    -0.49
    Downloadha
    -0.49
    gor
    -0.49
    owler
    -0.49
    ucket
    -0.48
    bara
    -0.48
    POSITIVE LOGITS
     vulner
    0.60
    ãĥ¼ãĥĨ
    0.58
    ãĤ½
    0.57
     warr
    0.56
     adolesc
    0.55
     challeng
    0.54
     4090
    0.54
    ãĤ©
    0.53
    Ear
    0.52
     predec
    0.51
    Activations Density 6.208%

    No Known Activations