© 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. 10-RES-JB
    11. 18882
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting incidents to authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to reporting incidents or complaints to authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symbolism
    -0.75
     nostalgia
    -0.71
     symmetry
    -0.70
     layouts
    -0.68
     immortality
    -0.67
     Atkins
    -0.65
     glide
    -0.65
    gemony
    -0.63
     calculus
    -0.63
     alignment
    -0.63
    POSITIVE LOGITS
     hotline
    1.46
    police
    1.15
     promptly
    1.08
     enqu
    1.08
    Police
    1.08
     Incident
    1.07
    mbuds
    1.05
     police
    1.04
     Investigations
    1.03
     Police
    0.99
    Activations Density 0.402%

    No Known Activations