INDEX

Explanations

phrases emphasizing equality or similarity among multiple subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 callers

-0.71

protoimpl

-0.70

uegos

-0.68

 Kanna

-0.66

 NDEBUG

-0.65

 ſche

-0.64

]`

-0.63

Yol

-0.63

 reaſon

-0.62

 becauſe

-0.62

POSITIVE LOGITS

 both

0.72

all

0.70

GraphicsUnit

0.64

 marked

0.64

DropTable

0.61

 getAll

0.60

!*\

0.60

getAll

0.58

 Firstly

0.56

gså

0.56

Activations Density 0.112%

phrases emphasizing equality or similarity among multiple subjects

No Comments

No Known Activations

phrases emphasizing equality or similarity among multiple subjects

No Comments

No Known Activations