© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7263
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific type of weapon - the AR-15 rifle

    oai_token-act-pair · gpt-3.5-turbo

    references to the AR (Assault Rifle) models, particularly AR-15 and AR-9

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

    No Comments

    Negative Logits
    hower
    -0.84
    éĹĺ
    -0.79
    cake
    -0.75
    ãĥĩãĤ£
    -0.74
     Pelosi
    -0.72
    eners
    -0.70
     Rollins
    -0.68
     Mercury
    -0.67
    urized
    -0.65
     Tid
    -0.64
    POSITIVE LOGITS
    ENA
    0.95
    ansas
    0.87
    RR
    0.86
    RAY
    0.86
    RL
    0.86
    OUND
    0.85
    ELY
    0.80
    LY
    0.77
    ANGE
    0.76
    RES
    0.76
    Activations Density 0.008%

    No Known Activations