INDEX

Explanations

references to numbered lists, items, or citations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 BoxFit

-0.71

SafeMath

-0.68

 onPostExecute

-0.67

runApp

-0.58

riwal

-0.57

.}\

-0.55

ătoare

-0.54

]-->

-0.53

̍t

-0.53

hwar

-0.53

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.82

 kasarigan

0.64

boil

0.51

сылкі

0.49

 Baillargeon

0.49

SharedCtor

0.48

 Infór

0.47

sizeCache

0.47

)**

0.47

الدراسه

0.47

Activations Density 0.503%

references to numbered lists, items, or citations within the text

No Comments

No Known Activations