© 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. 10-RES-JB
    11. 8193
    Prev
    Next
    INDEX
    Explanations

    words related to negative or derogatory comments or actions towards someone

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "belittle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regulation
    -0.61
    uncture
    -0.59
    ally
    -0.59
    oleon
    -0.58
    andals
    -0.57
    arty
    -0.57
    ority
    -0.56
     CLR
    -0.56
     appointment
    -0.55
    hibition
    -0.55
    POSITIVE LOGITS
    gian
    1.21
    ieving
    1.18
    iever
    1.17
    ievers
    1.14
    ichick
    1.13
    ieve
    1.08
    ieved
    1.06
    ittle
    1.04
    oved
    1.02
    abor
    0.99
    Activations Density 0.014%

    No Known Activations