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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 4332
    Prev
    Next
    INDEX
    Explanations

    incidents captured on video or audio recordings

    oai_token-act-pair · gpt-3.5-turbo

    references to video footage or recordings related to incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.85
    女
    -0.80
    âĺ
    -0.74
     laure
    -0.71
    izons
    -0.70
    iasis
    -0.70
     perman
    -0.69
    arth
    -0.69
    itte
    -0.69
    Tier
    -0.67
    POSITIVE LOGITS
     conversations
    1.14
     interviews
    1.03
     events
    0.99
     proceedings
    0.98
     encounters
    0.97
     gunshots
    0.95
     executions
    0.94
     conversation
    0.91
     footage
    0.91
     interrogation
    0.90
    Activations Density 0.208%

    No Known Activations