© 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. 7-RES-JB
    11. 9892
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of conflict or confrontation involving multiple parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tolkien
    -0.79
     UNESCO
    -0.77
     ç¥ŀ
    -0.75
     optim
    -0.75
    olkien
    -0.74
    çļ
    -0.68
     univers
    -0.67
     splend
    -0.66
    ~~
    -0.64
     trillions
    -0.64
    POSITIVE LOGITS
     burglary
    1.18
     police
    1.04
     burgl
    1.01
     robbery
    1.01
     deputies
    1.00
    Police
    0.99
     detectives
    0.97
     homicide
    0.92
     felony
    0.92
     juveniles
    0.91
    Activations Density 1.431%

    No Known Activations