© 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. 3-RES-JB
    11. 6131
    Prev
    Next
    INDEX
    Explanations

    information about violent attacks carried out by perpetrators

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents or attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glomer
    -0.72
    theless
    -0.70
    ETA
    -0.67
    zl
    -0.65
    clud
    -0.62
    }}}
    -0.61
    FORMATION
    -0.61
    dit
    -0.60
     mineral
    -0.60
    ERE
    -0.59
    POSITIVE LOGITS
     spree
    1.13
     perpetrated
    0.86
    ocalypse
    0.81
    attack
    0.81
     attack
    0.81
     attacks
    0.79
    abad
    0.76
     assault
    0.76
    ivity
    0.74
    iveness
    0.74
    Activations Density 0.033%

    No Known Activations