© 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. 17691
    Prev
    Next
    INDEX
    Explanations

    words related to safety and precautionary measures

    oai_token-act-pair · gpt-3.5-turbo

    imperative phrases or commands directing actions or suggestions

    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
    edge
    -0.78
    emale
    -0.75
    album
    -0.75
    ometown
    -0.62
    apo
    -0.62
    lap
    -0.61
    hell
    -0.59
    "]=>
    -0.59
    ungle
    -0.59
    ilver
    -0.58
    POSITIVE LOGITS
     yourselves
    1.21
     yourself
    1.19
     wisely
    0.85
     Yourself
    0.83
     ye
    0.79
     your
    0.78
     carefully
    0.75
     YOUR
    0.73
     preferably
    0.73
     ASAP
    0.71
    Activations Density 0.231%

    No Known Activations