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. 9-RES-JB
    6. 7952
    Prev
    Next
    INDEX
    Explanations

    tools or weapons commonly associated with potentially harmful or violent situations

    oai_token-act-pair · gpt-3.5-turbo

    objects associated with violence or tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omal
    -0.75
     Events
    -0.71
     Rooms
    -0.68
    rians
    -0.67
     Regions
    -0.67
     Buildings
    -0.67
     Restaur
    -0.67
     Halls
    -0.65
    physical
    -0.65
     Vehicles
    -0.65
    POSITIVE LOGITS
     strapped
    1.11
     holder
    1.09
     dangling
    1.08
     clenched
    1.04
     protr
    1.03
     cutter
    1.02
     grasped
    0.98
     shoved
    0.98
     jammed
    0.97
     launcher
    0.95
    Activations Density 0.274%

    No Known Activations