© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 21955
    Prev
    Next
    INDEX
    Explanations

    references to police activities or investigations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of police activity

    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
    ulence
    -0.69
     Economist
    -0.68
    gow
    -0.67
    zsche
    -0.65
    fuck
    -0.64
    hered
    -0.63
    士
    -0.62
     Convert
    -0.61
    ittered
    -0.58
     Dil
    -0.58
    POSITIVE LOGITS
     investigating
    1.44
     conducting
    1.22
     searching
    1.20
     inspecting
    1.14
     probing
    1.13
     patrolling
    1.12
     assisting
    1.12
     checking
    1.11
     reviewing
    1.08
     verifying
    1.08
    Activations Density 0.123%

    No Known Activations