© 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. 1695
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or political struggle and conflict

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to struggles or efforts against various societal issues

    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
    ascript
    -0.77
    /-
    -0.70
    mson
    -0.65
    Ter
    -0.64
    Redd
    -0.64
     Seym
    -0.64
    undai
    -0.63
     Birthday
    -0.61
    66666666
    -0.61
     Minor
    -0.61
    POSITIVE LOGITS
     against
    0.94
     waged
    0.90
    athon
    0.82
     toward
    0.79
    Enlarge
    0.77
     underway
    0.76
     effort
    0.76
    iest
    0.76
     combating
    0.75
    ggle
    0.75
    Activations Density 0.156%

    No Known Activations