© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    sentences with a call to action or questions related to addressing challenges

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their associated contexts

    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
     unders
    -0.76
     challeng
    -0.73
     brut
    -0.71
     dwar
    -0.71
     thirst
    -0.71
     rall
    -0.69
     hust
    -0.67
     scorp
    -0.65
     tame
    -0.65
     testament
    -0.65
    POSITIVE LOGITS
     Flavoring
    1.15
     Again
    1.09
     Depending
    1.05
    Reviewer
    1.05
     Examples
    1.02
     Therefore
    1.02
     Specifically
    1.01
    sbm
    0.99
     However
    0.99
     Usually
    0.98
    Activations Density 0.290%

    No Known Activations