INDEX

Explanations

mathematical or programming symbols and terms related to definitions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.71

-0.68

-0.65

in

-0.63

as

-0.60

-0.59

for

-0.58

-0.57

 again

-0.56

POSITIVE LOGITS

WebElementEntity

1.29

 "..\..\..\

1.24

 "..\..\

1.22

 مرئيه

1.19

 disambiguazione

1.19

 صوتيه

1.16

 myſelf

1.15

$_"

1.12

脚注の使い方

1.10

thâu

1.08

Activations Density 0.567%

mathematical or programming symbols and terms related to definitions and equations

No Comments

No Known Activations