INDEX

Explanations

expressions of conflict or negative emotions among characters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.79

IndentedString

-0.77

libft

-0.74

 himſelf

-0.74

 himself

-0.73

Ārējās

-0.66

 مُعرِّف

-0.66

 وتسجيلات

-0.64

namics

-0.64

himself

-0.64

POSITIVE LOGITS

 collectively

0.89

 collective

0.73

 unanimously

0.73

collective

0.61

各自

0.60

 kollek

0.57

 colectiva

0.56

 unanimous

0.56

 Collective

0.53

纷纷

0.53

Activations Density 0.380%

expressions of conflict or negative emotions among characters

No Comments

No Known Activations