INDEX

Explanations

references to significant moral or ethical conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 things

-0.94

 really

-0.83

 very

-0.80

 REALLY

-0.77

 thing

-0.77

 cosas

-0.76

 dingen

-0.73

 montón

-0.73

really

-0.72

 basically

-0.72

POSITIVE LOGITS

]='\

0.82

 captivating

0.64

tiously

0.62

++];

0.61

 ensuing

0.58

tvguidetime

0.58

 sämtliche

0.58

 Consequently

0.58

 nebst

0.58

唯有

0.57

Activations Density 1.077%

references to significant moral or ethical conflicts

No Comments

No Known Activations

references to significant moral or ethical conflicts

No Comments

No Known Activations