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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17194
    Prev
    Next
    INDEX
    Explanations

    law enforcement and security-related terms, such as "security guards", "police", and "deputies"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to law enforcement and emergency response

    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
     Practices
    -0.78
     fantas
    -0.71
     dreams
    -0.69
     calendar
    -0.66
     Pinterest
    -0.66
    ivalent
    -0.66
     Previously
    -0.64
     Contracts
    -0.63
    dream
    -0.63
    Ranked
    -0.63
    POSITIVE LOGITS
     subdued
    1.26
     subdu
    1.21
     overpowered
    1.10
     rescue
    1.04
     incapac
    1.04
     apprehended
    1.02
     rescued
    1.01
     apprehend
    1.00
     gunfire
    1.00
     escape
    0.99
    Activations Density 0.376%

    No Known Activations