INDEX

Explanations

terms and phrases related to scientific notation and formatting in mathematical expressions

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

<table>

-0.54

-0.52

+=

-0.51

ாக

-0.51

addEventListener

-0.51

pages

-0.51

rel

-0.51

-=

-0.50

POSITIVE LOGITS

NUMX

0.83

 ExecuteAsync

0.79

spectos

0.79

^(@)

0.78

enumi

0.77

MessageTagHelper

0.74

〢

0.73

Хьажоргаш

0.67

 itſelf

0.66

tvguidetime

0.66

Activations Density 0.084%

terms and phrases related to scientific notation and formatting in mathematical expressions

No Comments

No Known Activations