© 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. 2-RES-JB
    11. 9434
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency or crime scenes

    oai_token-act-pair · gpt-3.5-turbo

    references to the scene of an event or incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.97
    berman
    -0.92
    ongyang
    -0.85
    achev
    -0.82
    heit
    -0.80
    icrobial
    -0.79
    iago
    -0.78
    gements
    -0.76
    amn
    -0.75
    utm
    -0.75
    POSITIVE LOGITS
     scenes
    1.01
     Scene
    0.94
     Scenes
    0.92
    Dialogue
    0.92
     Veter
    0.91
     scene
    0.88
    Capture
    0.75
    scene
    0.74
     VIDE
    0.71
     Shooting
    0.68
    Activations Density 0.011%

    No Known Activations