© 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. 10658
    Prev
    Next
    INDEX
    Explanations

    phrases related to opting out or agreement in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to opting out of agreements or services

    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
    hurst
    -0.69
     depths
    -0.66
     pests
    -0.64
    sworth
    -0.64
     Coff
    -0.64
     Helic
    -0.60
     Gazette
    -0.60
     Illustrated
    -0.58
     Lod
    -0.56
     Lau
    -0.56
    POSITIVE LOGITS
    ocl
    0.78
    wagen
    0.77
    haps
    0.75
     bandwagon
    0.74
    vironment
    0.67
     guiActiveUn
    0.67
    analy
    0.66
    trak
    0.66
    ersen
    0.65
    idas
    0.65
    Activations Density 0.085%

    No Known Activations