© 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. 11-RES-JB
    11. 18527
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to have"

    oai_token-act-pair · gpt-3.5-turbo

    future actions and obligations expressed in verbs and modal verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.77
    Adams
    -0.74
    answered
    -0.71
     minds
    -0.66
    Jun
    -0.65
     Guru
    -0.64
    soType
    -0.64
     Blackwell
    -0.62
    quickShipAvailable
    -0.61
     Fern
    -0.61
    POSITIVE LOGITS
     contain
    1.56
     consist
    1.46
     resemble
    1.36
     incorporate
    1.32
     feature
    1.29
     boast
    1.28
     utilize
    1.27
     rely
    1.19
     include
    1.19
     emit
    1.18
    Activations Density 0.247%

    No Known Activations