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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20729
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting incidents or issues to authorities or police

    oai_token-act-pair · gpt-3.5-turbo

    instances of reporting to authorities or law enforcement

    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
    anka
    -0.75
    çĶ°
    -0.72
    Untitled
    -0.72
    maker
    -0.68
    Synopsis
    -0.68
    puff
    -0.68
    neck
    -0.67
    raham
    -0.67
     excerpt
    -0.67
    dra
    -0.66
    POSITIVE LOGITS
     authorities
    1.67
     police
    1.29
     regulators
    1.24
     superiors
    1.22
     investigators
    1.22
     law
    1.08
    police
    1.07
     Authorities
    1.07
     customs
    1.06
     cops
    1.05
    Activations Density 0.320%

    No Known Activations