© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5187
    Prev
    Next
    INDEX
    Explanations

    words related to rigidity or inflexibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rigidity or stiffness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.89
    hex
    -0.75
     Hiroshima
    -0.73
    obyl
    -0.70
     Occupations
    -0.69
     Shutterstock
    -0.67
    uyomi
    -0.66
    orea
    -0.65
    jamin
    -0.64
    opus
    -0.61
    POSITIVE LOGITS
    est
    1.06
    ening
    1.02
    eners
    1.01
    eling
    0.99
    nesses
    0.98
    ened
    0.96
    er
    0.96
     stiff
    0.88
    ly
    0.87
    eness
    0.84
    Activations Density 0.021%

    No Known Activations