Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5643
    Prev
    Next
    INDEX
    Explanations

    keywords related to prison inmates and their experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to inmates in a correctional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pp
    -0.77
    rous
    -0.74
    opic
    -0.73
     Nare
    -0.70
    lag
    -0.70
    drive
    -0.68
     Obst
    -0.64
    Bus
    -0.63
     Oslo
    -0.62
    OPA
    -0.62
    POSITIVE LOGITS
     inmates
    1.22
     inmate
    1.06
    icts
    0.93
    iaries
    0.85
     cylinders
    0.81
     incarcerated
    0.76
     closet
    0.75
     prisons
    0.75
     Correctional
    0.74
    mates
    0.74
    Activations Density 0.010%

    No Known Activations