© 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. 2-RES-JB
    11. 1663
    Prev
    Next
    INDEX
    Explanations

    references to cruelty and inhumanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to harsh or severe treatment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACP
    -0.81
    inoa
    -0.76
    ainers
    -0.71
    aintain
    -0.69
    avez
    -0.69
     Banking
    -0.68
    rity
    -0.68
    ovember
    -0.68
    igate
    -0.68
    BU
    -0.67
    POSITIVE LOGITS
     cruel
    1.01
     undermin
    0.84
     irony
    0.83
     cruelty
    0.81
     inhuman
    0.79
     torment
    0.77
     injustice
    0.77
     Cruel
    0.76
     confinement
    0.76
     killers
    0.76
    Activations Density 0.005%

    No Known Activations