© 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. 6632
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or product names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific academic faculties or types of institutions

    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
     reluct
    -0.79
     eleph
    -0.78
     accomp
    -0.72
     occas
    -0.72
     arrang
    -0.71
     tremend
    -0.69
     EFF
    -0.67
     arri
    -0.67
     enthusi
    -0.67
     "âĢ¦
    -0.65
    POSITIVE LOGITS
    intosh
    0.89
    ename
    0.87
    rylic
    0.87
    endish
    0.83
    umeric
    0.81
    apest
    0.79
    netic
    0.77
    castle
    0.76
    oslav
    0.76
    atomic
    0.76
    Activations Density 0.153%

    No Known Activations