© 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. 7-RES-JB
    11. 21431
    Prev
    Next
    INDEX
    Explanations

    reports of discoveries or findings, specifically related to individuals being found

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the discovery of deceased individuals

    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
    yip
    -0.78
     tert
    -0.72
    dayName
    -0.71
    lishes
    -0.68
    creation
    -0.67
    ankind
    -0.65
    eries
    -0.64
    dos
    -0.62
    earned
    -0.61
     modulation
    -0.60
    POSITIVE LOGITS
     guilty
    0.90
    âĸĪ
    0.85
    Ô
    0.77
     Alive
    0.76
     dead
    0.76
     tampering
    0.76
     Guilty
    0.75
    dylib
    0.74
     alive
    0.71
    Ĥİ
    0.70
    Activations Density 0.044%

    No Known Activations