© 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. 7244
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or structural elements in the text

    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
     toget
    -0.87
    etheless
    -0.84
     dispos
    -0.77
     culp
    -0.75
     carbohyd
    -0.72
     pipelines
    -0.71
     constit
    -0.69
     fixtures
    -0.68
     accumulating
    -0.67
     nostalg
    -0.66
    POSITIVE LOGITS
     Lights
    0.98
     Hour
    0.93
     Unknown
    0.90
     Mountains
    0.90
     Heights
    0.89
     Ends
    0.88
     Future
    0.88
     Mask
    0.87
     Hands
    0.87
     Replacement
    0.87
    Activations Density 0.498%

    No Known Activations