© 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. 4-RES-JB
    11. 20672
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or pointing out issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetitive phrases or patterns in sentences

    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
    §
    -0.70
    rencies
    -0.65
    ¬¼
    -0.64
    ¦
    -0.61
     tooltip
    -0.60
    ãĥ¼ãĥ
    -0.59
    herent
    -0.58
    Īè
    -0.58
    iple
    -0.57
    izen
    -0.56
    POSITIVE LOGITS
     yeah
    1.01
     etc
    0.94
     namely
    0.88
     albeit
    0.84
     sir
    0.83
     huh
    0.83
     but
    0.80
     eh
    0.80
     irrespective
    0.80
     although
    0.78
    Activations Density 0.638%

    No Known Activations