© 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. 0-RES-JB
    11. 4070
    Prev
    Next
    INDEX
    Explanations

    references to or discussions about flight MH (Malaysia Airlines) incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to specific airline incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eln
    -0.75
     extrad
    -0.71
    omy
    -0.70
    acus
    -0.70
     semin
    -0.69
    ulo
    -0.68
    abet
    -0.67
    fle
    -0.67
     cul
    -0.66
    hell
    -0.66
    POSITIVE LOGITS
     Reserve
    1.26
    while
    0.85
    MH
    0.83
     Hawth
    0.76
     Boone
    0.71
     misunder
    0.69
     while
    0.69
     Haram
    0.69
    RAFT
    0.67
    eer
    0.67
    Activations Density 0.001%

    No Known Activations