INDEX

Explanations

programming-related keywords and constructs, particularly those associated with user interface actions and threading

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Corbin

-0.50

webElementXpaths

-0.46

BufferException

-0.44

IBarButtonItem

-0.43

<bos>

-0.43

($"{

-0.43

----</

-0.42

Dữ

-0.42

em

-0.41

 thẳng

-0.41

POSITIVE LOGITS

 kasarigan

0.83

 للاسماء

0.70

 nakalista

0.66

rungsseite

0.64

 CreateTagHelper

0.62

 autorytatywna

0.61

XmlAccessType

0.60

createClass

0.59

 esternos

0.57

Sucesor

0.57

Activations Density 0.073%

programming-related keywords and constructs, particularly those associated with user interface actions and threading

No Comments

No Known Activations