© 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. 4-RES-JB
    11. 20706
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of impeachment

    oai_token-act-pair · gpt-3.5-turbo

    the word "Im" in various forms

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

    No Comments

    Negative Logits
    NetMessage
    -0.96
    Downloadha
    -0.77
     Skydragon
    -0.75
    ttes
    -0.73
    yards
    -0.73
     Nazis
    -0.72
     Chrys
    -0.71
     mars
    -0.71
     Warwick
    -0.70
     Remastered
    -0.68
    POSITIVE LOGITS
    ple
    1.31
    mediate
    1.26
    perfect
    1.24
    perial
    1.24
    mediately
    1.23
    unity
    1.16
    medi
    1.15
    posing
    1.13
    plement
    1.13
    agine
    1.12
    Activations Density 0.011%

    No Known Activations