© 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. 9-RES-JB
    11. 7310
    Prev
    Next
    INDEX
    Explanations

    instructions or tips with a strong emphasis on ensuring specific actions or items are in order

    oai_token-act-pair · gpt-3.5-turbo

    commands or instructions emphasizing actions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}
    -0.71
    enei
    -0.70
     Mehran
    -0.68
    kefeller
    -0.64
    ocaust
    -0.62
    edition
    -0.60
    ullah
    -0.60
    ulin
    -0.58
     Hussain
    -0.58
    "]
    -0.57
    POSITIVE LOGITS
     yourself
    1.50
     yourselves
    1.33
     your
    1.18
     Yourself
    1.16
    cknow
    1.10
     YOUR
    0.98
     preferably
    0.97
     sparing
    0.93
     wisely
    0.88
    your
    0.88
    Activations Density 0.535%

    No Known Activations