© 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. 16514
    Prev
    Next
    INDEX
    Explanations

    instructions or requirements for specific actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating requirements or necessities

    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
    Ń·
    -0.78
    ð
    -0.65
    grim
    -0.64
     miscar
    -0.60
     Dism
    -0.60
    ihu
    -0.60
    threat
    -0.60
     Seym
    -0.59
    ouk
    -0.58
    lambda
    -0.58
    POSITIVE LOGITS
    lessly
    1.20
     to
    0.84
    n
    0.78
     patience
    0.77
     permission
    0.76
    rals
    0.69
    ful
    0.69
     something
    0.69
     helpers
    0.68
     assistance
    0.66
    Activations Density 0.071%

    No Known Activations