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. 9481
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement activities and incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement officers and their actions

    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
     Seeds
    -0.78
     surrog
    -0.72
    uctions
    -0.72
     Publishers
    -0.71
     cryptocurrencies
    -0.70
     seeds
    -0.70
     Collider
    -0.70
    çķ
    -0.69
     coales
    -0.68
    isSpecialOrderable
    -0.65
    POSITIVE LOGITS
    duty
    1.16
     superv
    1.15
     duty
    1.14
     patrolling
    1.11
     supervisors
    1.06
     patrol
    1.02
    trained
    1.02
     trained
    0.99
    uties
    0.99
     duties
    0.99
    Activations Density 0.998%

    No Known Activations