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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 16837
    Prev
    Next
    INDEX
    Explanations

    terms related to military equipment and operations

    oai_token-act-pair · gpt-3.5-turbo

    negative references to military equipment or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sson
    -0.71
    inen
    -0.67
     Cla
    -0.66
     cous
    -0.64
     moder
    -0.63
     obst
    -0.63
     bona
    -0.61
     Cullen
    -0.61
     fra
    -0.61
     "$:/
    -0.61
    POSITIVE LOGITS
    shaped
    1.11
    dimensional
    0.98
    level
    0.98
    bomb
    0.92
    plus
    0.91
    series
    0.91
    chan
    0.89
    sized
    0.88
    Unit
    0.88
    bodied
    0.87
    Activations Density 0.055%

    No Known Activations