© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6114
    Prev
    Next
    INDEX
    Explanations

    instances related to the Sandy Hook tragedy

    oai_token-act-pair · gpt-3.5-turbo

    references to the Sandy Hook incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescent
    -0.98
    orney
    -0.90
    unct
    -0.84
    aird
    -0.80
    ioch
    -0.77
    orne
    -0.76
    pires
    -0.74
    ional
    -0.74
    uador
    -0.73
    usc
    -0.73
    POSITIVE LOGITS
     Hook
    1.26
     Springs
    0.93
     Sandy
    0.89
     Creek
    0.87
     Kou
    0.85
    brook
    0.82
    storm
    0.78
     Harbor
    0.77
     Harbour
    0.77
     Leone
    0.77
    Activations Density 0.042%

    No Known Activations