INDEX

Explanations

phrases that indicate subjective opinions or evaluations about products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bandeja

-0.46

ressum

-0.46

 Numerade

-0.46

WebElementEntity

-0.45

########.

-0.45

 гей

-0.44

abá

-0.44

lottesville

-0.44

InteropServices

-0.42

endregion

-0.42

POSITIVE LOGITS

henswürdigkeiten

0.66

 FLASH

0.65

stackSize

0.61

 Cortex

0.60

errHandler

0.59

__);

0.59

(;;)

0.58

 surla

0.58

presso

0.58

Жит

0.57

Activations Density 0.428%

phrases that indicate subjective opinions or evaluations about products or experiences

No Comments

No Known Activations