© 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. 12588
    Prev
    Next
    INDEX
    Explanations

    phrases related to commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    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
    ibur
    -0.97
     sustained
    -0.80
     gunned
    -0.71
     sustaining
    -0.70
     grip
    -0.70
     choking
    -0.69
     bush
    -0.67
     choked
    -0.67
     dere
    -0.66
     meddling
    -0.65
    POSITIVE LOGITS
     Each
    1.60
     Depending
    1.52
     Usually
    1.44
     Ideally
    1.39
     Afterwards
    1.37
     Additionally
    1.36
     Typically
    1.36
     Then
    1.35
     Alternatively
    1.35
     Otherwise
    1.32
    Activations Density 0.411%

    No Known Activations