© 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. 9-RES-JB
    11. 17173
    Prev
    Next
    INDEX
    Explanations

    phrases related to innocence and guilt, particularly phrases referring to innocent individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to innocent individuals in the context of marginalization or victimization

    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
    ingo
    -0.76
    è¦ļéĨĴ
    -0.71
    orders
    -0.70
    riber
    -0.70
    division
    -0.68
    ribed
    -0.68
     Extrem
    -0.66
    ANN
    -0.66
    TOP
    -0.65
    yi
    -0.65
    POSITIVE LOGITS
     bystanders
    1.40
     bystand
    1.37
     innocent
    1.02
     civilians
    0.96
     victims
    0.89
     innoc
    0.82
    ocent
    0.75
     souls
    0.71
     prey
    0.71
     unborn
    0.70
    Activations Density 0.025%

    No Known Activations