© 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. 9706
    Prev
    Next
    INDEX
    Explanations

    references to specific roles or functions within a system, such as in healthcare, government, or society

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "role" in various contexts

    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
    False
    -0.72
    Latest
    -0.71
     Bulg
    -0.67
    bones
    -0.67
     Trout
    -0.64
    ãĥ©ãĥ³
    -0.64
     Rapt
    -0.64
     Uri
    -0.63
    REAM
    -0.63
    yg
    -0.62
    POSITIVE LOGITS
    playing
    1.02
     roles
    0.99
     reversal
    0.86
     role
    0.84
    role
    0.76
    model
    0.74
     models
    0.73
    annel
    0.72
    entials
    0.72
    uty
    0.71
    Activations Density 0.037%

    No Known Activations