INDEX

Explanations

phrases indicating cause-and-effect relationships and dependencies

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

 صوتيه

-0.80

 '\\;'

-0.77

 GenerationType

-0.76

 تضيفلها

-0.75

RegressionTest

-0.75

ValueGenerated

-0.74

 дописавши

-0.73

 للمعارف

-0.73

 Infórmanos

-0.72

帖最后由

-0.72

POSITIVE LOGITS

それだけ

0.62

 also

0.61

 must

0.60

 correspondingly

0.56

 corresponding

0.54

 therefore

0.53

 damit

0.52

 berarti

0.52

 consequently

0.50

Activations Density 0.514%

phrases indicating cause-and-effect relationships and dependencies

No Comments

No Known Activations