© 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. 7-RES-JB
    11. 8837
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or control

    oai_token-act-pair · gpt-3.5-turbo

    references to control or possession by different agents or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coverage
    -0.69
    Ann
    -0.68
    atten
    -0.65
    solid
    -0.63
     redes
    -0.62
    autical
    -0.62
     Sapp
    -0.61
    icut
    -0.60
    rely
    -0.60
     Scotia
    -0.60
    POSITIVE LOGITS
     traffickers
    0.73
     wielded
    0.66
    offs
    0.66
    lopp
    0.66
    esson
    0.65
    ulator
    0.64
    igators
    0.64
     winds
    0.63
     cartel
    0.62
     smugglers
    0.61
    Activations Density 0.033%

    No Known Activations