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. 3-RES-JB
    6. 8509
    Prev
    Next
    INDEX
    Explanations

    instances related to isolation or confinement

    oai_token-act-pair · gpt-3.5-turbo

    references to solitary confinement and related themes of isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppers
    -0.83
    ichick
    -0.71
    Mass
    -0.69
    amins
    -0.69
    efficients
    -0.67
    nostic
    -0.67
    soDeliveryDate
    -0.67
    ACTED
    -0.67
    inki
    -0.66
    rote
    -0.66
    POSITIVE LOGITS
     confinement
    1.52
     solitary
    1.21
    uously
    0.69
     minded
    0.69
    spection
    0.68
     lone
    0.67
    theless
    0.66
    itud
    0.66
     plum
    0.65
    uous
    0.65
    Activations Density 0.006%

    No Known Activations