© 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. 3174
    Prev
    Next
    INDEX
    Explanations

    mentions of violent and tragic events, particularly involving deaths and atrocities

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

    references to violence and human rights abuses

    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
     ECO
    -0.77
    BuyableInstoreAndOnline
    -0.74
     optimism
    -0.72
     Sunshine
    -0.71
    clinton
    -0.69
     reassuring
    -0.67
    velength
    -0.66
     Cooperative
    -0.66
     understatement
    -0.64
     Peach
    -0.63
    POSITIVE LOGITS
     decap
    1.39
     executions
    1.36
     cannibal
    1.31
     corpses
    1.27
     captives
    1.20
     mut
    1.20
     execution
    1.20
     slaughtered
    1.19
     cruc
    1.16
     butcher
    1.15
    Activations Density 0.445%

    No Known Activations