© 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. 7-RES-JB
    11. 23514
    Prev
    Next
    INDEX
    Explanations

    names of individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    unknown or unspecified entities or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    voy
    -0.73
    BOOK
    -0.67
     expressive
    -0.64
     pains
    -0.62
     unintended
    -0.61
     practicable
    -0.58
    uve
    -0.58
    APH
    -0.58
     resemb
    -0.57
     disobedience
    -0.57
    POSITIVE LOGITS
    buster
    1.14
    geon
    1.01
    irk
    0.98
    rat
    0.97
    ett
    0.91
    regate
    0.88
    ernel
    0.88
    etsu
    0.87
    adel
    0.87
    iewicz
    0.86
    Activations Density 0.034%

    No Known Activations