© 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. 7-RES-JB
    11. 21129
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or protective responsibilities and relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to custody and guardianship

    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
     Fighters
    -0.77
    cloth
    -0.71
     Kamp
    -0.70
    lished
    -0.68
    AAF
    -0.66
     Speedway
    -0.65
    asted
    -0.65
    bers
    -0.65
    bed
    -0.61
     Schumer
    -0.61
    POSITIVE LOGITS
    hip
    1.32
    hips
    1.00
     guardians
    0.94
    ial
    0.87
     Cust
    0.86
     angel
    0.86
    esses
    0.78
     stewards
    0.78
     custod
    0.76
    ess
    0.76
    Activations Density 0.110%

    No Known Activations