© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 5113
    Prev
    Next
    INDEX
    Explanations

    negative or harmful language, such as derogatory or inappropriate terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative or harmful content and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tested
    -0.86
    rage
    -0.86
    emis
    -0.82
    hung
    -0.81
    united
    -0.81
    wright
    -0.80
    lite
    -0.80
    abiding
    -0.79
    winning
    -0.78
    bender
    -0.78
    POSITIVE LOGITS
     behavior
    1.13
     materials
    1.13
     material
    1.12
     behaviour
    1.12
     activities
    1.11
     activity
    1.10
     conduct
    1.06
     behaviors
    1.06
     situations
    1.03
     items
    1.02
    Activations Density 0.267%

    No Known Activations