© 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. 7-RES-JB
    11. 1590
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenging or questioning

    oai_token-act-pair · gpt-3.5-turbo

    references to specific scientific terms or concepts related to cellular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.66
     Rohing
    -0.64
     stunts
    -0.63
     condem
    -0.62
     Rohingya
    -0.60
     Rudd
    -0.59
     Patriarch
    -0.58
     reflex
    -0.57
     Hurt
    -0.57
     Nau
    -0.57
    POSITIVE LOGITS
    ï¸ı
    1.08
    âĶĢâĶĢ
    0.87
    ternity
    0.84
    _>
    0.82
    ishable
    0.81
    âĶĢâĶĢâĶĢâĶĢ
    0.80
    âĵĺ
    0.76
    uthor
    0.76
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.75
    ²
    0.74
    Activations Density 0.231%

    No Known Activations