© 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. 10-RES-JB
    11. 13956
    Prev
    Next
    INDEX
    Explanations

    words related to tragic events, such as injuries, fatalities, and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    situations involving harm, victims, and the implications of violence or legal issues

    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
     caut
    -0.70
     blat
    -0.68
    apest
    -0.65
     enqu
    -0.61
    icult
    -0.55
     advoc
    -0.54
     compan
    -0.54
    Firstly
    -0.53
     ner
    -0.53
     REPL
    -0.52
    POSITIVE LOGITS
     during
    0.91
     amid
    0.79
     onstage
    0.77
    thood
    0.74
    during
    0.74
     stemming
    0.73
     pursuant
    0.73
     after
    0.73
     afterward
    0.72
     when
    0.72
    Activations Density 0.775%

    No Known Activations