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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 39
    Prev
    Next
    INDEX
    Explanations

    incidents of handcuffing or mentions of handcuffs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being restrained or handcuffed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Destination
    -0.73
    ONSORED
    -0.73
    ynt
    -0.70
    amins
    -0.70
     Flavoring
    -0.70
     Reasons
    -0.70
    soType
    -0.69
     Scotia
    -0.68
    atican
    -0.66
    emi
    -0.66
    POSITIVE LOGITS
     shack
    1.01
     handcuffed
    1.01
     straps
    0.97
     handcuffs
    0.93
     strap
    0.92
     restraints
    0.92
     strapped
    0.90
     restrain
    0.84
     clasp
    0.84
     handc
    0.83
    Activations Density 0.029%

    No Known Activations