© 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. 14528
    Prev
    Next
    INDEX
    Explanations

    words related to violent actions and weapons

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of physical actions, particularly those involving throwing or launching

    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
    Redd
    -0.69
     Janeiro
    -0.65
     Lok
    -0.62
    Recomm
    -0.62
    uren
    -0.61
     Nug
    -0.61
     Sok
    -0.60
    priv
    -0.59
     WHO
    -0.59
    Poor
    -0.59
    POSITIVE LOGITS
    geoning
    0.86
    ooter
    0.83
    atility
    0.76
    storms
    0.75
    ibur
    0.75
    ioned
    0.74
    engers
    0.73
    ooters
    0.73
     detectors
    0.73
    ting
    0.73
    Activations Density 0.218%

    No Known Activations