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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3941
    Prev
    Next
    INDEX
    Explanations

    instances where someone is asking for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include requests or demands

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

    No Comments

    Negative Logits
    port
    -0.78
    fleet
    -0.75
    founded
    -0.74
    Link
    -0.72
    edin
    -0.71
    may
    -0.69
    Center
    -0.68
    link
    -0.67
    aut
    -0.67
    leon
    -0.67
    POSITIVE LOGITS
    gery
    1.18
     forgiveness
    1.00
    geries
    0.97
     clarification
    0.94
     permission
    0.89
     refunds
    0.85
     captcha
    0.83
     reinforcements
    0.83
     inclusion
    0.82
    gotten
    0.81
    Activations Density 0.077%

    No Known Activations