INDEX

Explanations

phrases related to health, safety, and medical implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

tab

-0.44

 sort

-0.40

inck

-0.40

 stammer

-0.39

rischen

-0.39

zeh

-0.38

udos

-0.38

ran

-0.38

Cal

-0.38

 singur

-0.38

POSITIVE LOGITS

but

1.31

 nhưng

1.16

 pero

1.12

 mutta

1.09

 tetapi

1.06

 namun

1.06

 tapi

1.06

 ngunit

1.03

 אבל

1.01

 אך

0.99

Activations Density 0.554%

phrases related to health, safety, and medical implications

No Comments

No Known Activations