© 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. 23007
    Prev
    Next
    INDEX
    Explanations

    words related to violence and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms of "raw" material or experiences

    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
    ŃĶ
    -0.85
     Normandy
    -0.65
    uated
    -0.65
    uate
    -0.65
    ossession
    -0.64
     bubble
    -0.64
     Amend
    -0.64
    ucky
    -0.64
    arios
    -0.64
    eanor
    -0.62
    POSITIVE LOGITS
    raw
    1.28
    Pic
    0.88
    TPPStreamerBot
    0.88
    esome
    0.86
    lings
    0.83
    sth
    0.83
    inning
    0.82
    MpServer
    0.81
    RAW
    0.80
    ls
    0.80
    Activations Density 0.003%

    No Known Activations