INDEX

Explanations

phrases indicating uncertainty or possibility regarding outcomes and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للاسماء

-0.78

NameInMap

-0.72

 transfieras

-0.71

TagHelper

-0.69

ContentAsync

-0.67

 createSlice

-0.64

 uncomment

-0.63

évaluateur

-0.62

новниш

-0.62

 ivelany

-0.61

POSITIVE LOGITS

due

1.41

 caused

1.22

 attributable

1.05

due

1.04

 result

1.01

caused

0.98

 because

0.97

 debido

0.94

 devido

0.94

 driven

0.94

Activations Density 0.588%

phrases indicating uncertainty or possibility regarding outcomes and associations

No Comments

No Known Activations