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. 4-RES-JB
    6. 23921
    Prev
    Next
    INDEX
    Explanations

    phrases related to isolation or confinement

    oai_token-act-pair · gpt-3.5-turbo

    references to solitary confinement and its implications

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

    No Comments

    Negative Logits
    oppers
    -0.76
    ichick
    -0.71
     exch
    -0.70
    raught
    -0.68
    enic
    -0.67
    soDeliveryDate
    -0.67
    orah
    -0.67
    ermott
    -0.66
     Clash
    -0.66
    enegger
    -0.66
    POSITIVE LOGITS
     confinement
    1.69
     solitary
    1.19
    spection
    0.73
     inmate
    0.72
     dwellings
    0.69
    icol
    0.68
     prisoner
    0.68
    ism
    0.67
     minded
    0.67
     pen
    0.66
    Activations Density 0.013%

    No Known Activations