© 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. 2245
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb or phrase, possibly related to design or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving design intent or purpose

    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
    listed
    -0.75
    mentioned
    -0.72
    ua
    -0.65
    calling
    -0.64
     Forced
    -0.61
     Registrar
    -0.61
    browser
    -0.60
     banner
    -0.60
     Lots
    -0.60
     banners
    -0.59
    POSITIVE LOGITS
     withstand
    1.26
     accommodate
    1.19
     maximize
    1.15
     resemble
    1.13
     imitate
    1.12
     emulate
    1.11
     comply
    1.09
     inflict
    1.08
     deceive
    1.08
     mimic
    1.08
    Activations Density 0.131%

    No Known Activations