© 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. 9-RES-JB
    11. 18593
    Prev
    Next
    INDEX
    Explanations

    instances of violent or tragic events involving people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of violent deaths and crime-related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ennial
    -0.82
    issance
    -0.77
    ãĤ´ãĥ³
    -0.73
    ertain
    -0.73
    INESS
    -0.69
    amate
    -0.69
    HCR
    -0.69
     Names
    -0.68
    exclusive
    -0.68
     Costs
    -0.67
    POSITIVE LOGITS
     parked
    1.13
     attempting
    1.01
     accidentally
    0.97
     bicy
    0.95
     violently
    0.94
     drunk
    0.94
     takeoff
    0.93
     mistakenly
    0.91
     drunken
    0.91
     detonated
    0.91
    Activations Density 0.222%

    No Known Activations