© 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. 10-RES-JB
    11. 4378
    Prev
    Next
    INDEX
    Explanations

    phrases related to joining or aligning with a cause or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate participation or involvement in various movements or trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictionary
    -0.76
    pdf
    -0.68
    Lower
    -0.63
    grim
    -0.62
    pection
    -0.61
    sburg
    -0.60
    tenance
    -0.60
    DEN
    -0.60
    types
    -0.59
    gm
    -0.59
    POSITIVE LOGITS
     bandwagon
    1.46
     leaps
    0.82
     fray
    0.78
     wagon
    0.75
     heels
    0.73
     opportunity
    0.70
     hoops
    0.68
     conclusions
    0.68
     bait
    0.67
     temptation
    0.67
    Activations Density 0.123%

    No Known Activations