© 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. 9-RES-JB
    11. 16085
    Prev
    Next
    INDEX
    Explanations

    instances where someone is assuming or taking on a specific role or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    instances of characters or individuals assuming roles or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vine
    -0.76
    ileaks
    -0.70
    ochet
    -0.70
    raq
    -0.69
    ivers
    -0.67
    ucl
    -0.66
    tu
    -0.66
    apa
    -0.62
    testers
    -0.62
     informants
    -0.62
    POSITIVE LOGITS
     role
    1.67
     roles
    1.55
     mantle
    1.51
     duties
    1.43
     responsibilities
    1.42
     responsibility
    1.33
     throne
    1.25
     helm
    1.25
     reins
    1.24
     position
    1.24
    Activations Density 0.489%

    No Known Activations