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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15585
    Prev
    Next
    INDEX
    Explanations

    mention of gunshot wounds or gunshots themselves

    oai_token-act-pair · gpt-3.5-turbo

    references to gunshot-related injuries and their associated context

    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
    works
    -0.73
    âĶ
    -0.67
    eworks
    -0.64
    adan
    -0.63
    idity
    -0.63
    istry
    -0.62
    Works
    -0.62
    books
    -0.61
    essions
    -0.59
    land
    -0.58
    POSITIVE LOGITS
     gunshot
    3.62
     gunshots
    2.06
     bullet
    1.37
     stab
    1.31
     gunfire
    1.17
     handgun
    1.16
     firearm
    1.16
     shotgun
    1.15
     bullets
    1.15
     gunned
    1.13
    Activations Density 0.011%

    No Known Activations