© 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. 7-RES-JB
    11. 23522
    Prev
    Next
    INDEX
    Explanations

    Keywords related to terrorist attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorist attacks and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dit
    -0.98
    agin
    -0.69
    utical
    -0.68
    grain
    -0.67
    theless
    -0.66
     mineral
    -0.66
    agle
    -0.63
     Genie
    -0.62
    aird
    -0.62
    }}}
    -0.61
    POSITIVE LOGITS
     perpetrated
    1.08
     spree
    1.01
     against
    0.94
    abad
    0.93
     bombings
    0.93
     attacks
    0.90
     mastermind
    0.84
     retaliation
    0.82
     attack
    0.81
    attacks
    0.80
    Activations Density 0.065%

    No Known Activations