© 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. 7419
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts and problem-solving

    oai_token-act-pair · gpt-3.5-turbo

    instances of urgent actions and responses in a narrative context

    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
    prints
    -0.70
    ISC
    -0.69
    ocry
    -0.67
    jiang
    -0.66
    ļéĨĴ
    -0.63
    ortium
    -0.62
    rentices
    -0.62
     Dupl
    -0.59
     transcripts
    -0.59
     capped
    -0.58
    POSITIVE LOGITS
     intervene
    1.28
     evacuate
    1.10
     rescue
    1.00
     evacuation
    0.95
     warn
    0.94
     alert
    0.93
     remedy
    0.93
     urgently
    0.92
     precaution
    0.91
     vigil
    0.91
    Activations Density 0.721%

    No Known Activations