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. 11-RES-JB
    6. 3074
    Prev
    Next
    INDEX
    Explanations

    phrases related to being released from custody or jail

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals being released from custody or jail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orum
    -0.69
     Echoes
    -0.61
    ipes
    -0.60
     sourcing
    -0.60
    ggles
    -0.59
     Gears
    -0.59
    ifer
    -0.56
     Render
    -0.54
     Acquisition
    -0.54
     Demand
    -0.54
    POSITIVE LOGITS
     prisoner
    1.06
     uncond
    1.01
     prisoners
    0.97
     pending
    0.92
     alive
    0.91
     onto
    0.88
     handcuffs
    0.87
     captives
    0.86
    prison
    0.86
     from
    0.82
    Activations Density 0.063%

    No Known Activations