© 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. 1984
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    oai_token-act-pair · gpt-3.5-turbo

    infinitive phrases typically used to express purpose or intention

    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
     looms
    -0.72
    âĿ
    -0.68
    cuts
    -0.64
    quickShipAvailable
    -0.62
    Dur
    -0.61
     Hind
    -0.61
     replies
    -0.58
     HD
    -0.57
     URLs
    -0.56
    home
    -0.56
    POSITIVE LOGITS
     maximize
    1.09
     minimize
    1.04
     conserve
    1.01
     dismantle
    1.01
     avoid
    1.00
     find
    0.98
     provide
    0.97
     create
    0.97
     deprive
    0.96
     preserve
    0.96
    Activations Density 0.091%

    No Known Activations