© 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. 12-RES-JB
    11. 4664
    Prev
    Next
    INDEX
    Explanations

    details related to criminal incidents and accidents involving victims

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to individuals involved in violent incidents, particularly those related to shootings and assaults

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ĺħ
    -1.14
    è¦ļéĨĴ
    -0.93
    uggest
    -0.92
    izoph
    -0.89
    ichick
    -0.89
    ¥µ
    -0.83
    igmatic
    -0.83
    cffff
    -0.82
    hibit
    -0.82
    senal
    -0.82
    POSITIVE LOGITS
     suffered
    1.28
     died
    1.25
     sustained
    1.25
     succumbed
    1.18
     exited
    1.16
     was
    1.15
     survived
    1.15
     remained
    1.12
     underwent
    1.11
     fled
    1.10
    Activations Density 0.124%

    No Known Activations