© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22555
    Prev
    Next
    INDEX
    Explanations

    verbs indicating completion or fulfillment

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verbs "have" and "had."

    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
    soType
    -0.94
    ItemThumbnailImage
    -0.72
    isSpecialOrderable
    -0.67
    note
    -0.67
    abuse
    -0.65
    soDeliveryDate
    -0.63
    uty
    -0.62
     hostage
    -0.62
     Quote
    -0.62
    SAY
    -0.62
    POSITIVE LOGITS
     finished
    1.38
     completed
    1.36
     begun
    1.33
     reached
    1.29
     attained
    1.28
     exhausted
    1.26
     recovered
    1.25
     arrived
    1.25
     gotten
    1.24
     regained
    1.24
    Activations Density 0.219%

    No Known Activations