© 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. 9-RES-JB
    11. 6921
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance, threats, control, circumstances, investigation, and physical conditions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to surveillance and threat assessments

    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
    ument
    -0.70
    ubi
    -0.66
    pring
    -0.65
     Reply
    -0.64
     Room
    -0.63
     belie
    -0.62
     nerds
    -0.59
    iths
    -0.58
     contrace
    -0.58
     appealed
    -0.58
    POSITIVE LOGITS
     ausp
    1.40
     supervision
    1.15
     guise
    1.13
     circumstances
    1.02
     microscope
    1.01
     conditions
    0.94
     umbrella
    0.93
     banner
    0.91
    ħĭ
    0.85
     jurisdiction
    0.81
    Activations Density 0.183%

    No Known Activations