INDEX

Explanations

phrases that express inquiry or questioning, particularly in relation to reasons and explanations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ब्रेकडाउन

-0.64

matchCondition

-0.59

">//

-0.57

 SwiftUI

-0.55

 Infórmanos

-0.54

الحياه

-0.53

 Vienne

-0.52

IsMutable

-0.52

 gewiß

-0.52

UnusedPrivate

-0.51

POSITIVE LOGITS

?:

0.65

Почему

0.62

?).

0.61

Perché

0.61

的原因

0.60

 LUMP

0.60

왜

0.59

わざわざ

0.59

?}

0.58

Activations Density 0.342%

phrases that express inquiry or questioning, particularly in relation to reasons and explanations

No Comments

No Known Activations