© 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. 20525
    Prev
    Next
    INDEX
    Explanations

    negative news about criminal offenses involving minors

    oai_token-act-pair · gpt-3.5-turbo

    specific references to the age of children in distressing contexts

    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
     proport
    -0.77
     conduc
    -0.71
     redes
    -0.67
     shutter
    -0.64
     conclud
    -0.64
     enthusi
    -0.63
     brim
    -0.63
     sacrific
    -0.63
     reflections
    -0.63
     Borders
    -0.61
    POSITIVE LOGITS
    old
    1.64
    olds
    1.51
    Old
    1.18
    older
    1.11
    young
    1.10
    long
    1.09
    OLD
    1.05
    daughter
    1.03
    year
    0.99
    grade
    0.96
    Activations Density 0.020%

    No Known Activations