INDEX

Explanations

references to the concept of "word" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

RTSC

-0.63

IntoConstraints

-0.57

tagHelperRunner

-0.56

jspx

-0.54

InjectAttribute

-0.52

setVerticalGroup

-0.52

ftagPool

-0.52

tilli

-0.51

/**

-0.51

 Haines

-0.50

POSITIVE LOGITS

 word

2.22

Word

2.03

 words

1.94

 Word

1.93

word

1.90

 WORD

1.84

Words

1.77

 Words

1.73

words

1.70

 WORDS

1.70

Activations Density 0.102%

references to the concept of "word" and its variations in context

No Comments

No Known Activations