INDEX

Explanations

the repetition of the word "so" as a discourse marker

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

itez

-0.58

neurial

-0.57

RetentionPolicy

-0.57

RectangleBorder

-0.56

 kiệm

-0.55

XmlAccessType

-0.55

 killers

-0.53

 EconPapers

-0.53

 graveyard

-0.53

 AppDelegate

-0.53

POSITIVE LOGITS

0.64

 springfox

0.62

 onAnimation

0.59

 maș

0.58

WriteBarrier

0.58

 Derfor

0.57

 cref

0.57

 demais

0.57

 oprot

0.57

 MyBatis

0.57

Activations Density 0.055%

the repetition of the word "so" as a discourse marker

No Comments

No Known Activations