INDEX

Explanations

phrases indicating prioritization or significance in decision-making contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 AttributeSet

-0.94

AddTagHelper

-0.78

 TestBed

-0.69

BagLayout

-0.66

.$$

-0.65

CppMethod

-0.65

HtmlAttribute

-0.65

SOUNDBITE

-0.64

endregion

-0.64

 devrez

-0.64

POSITIVE LOGITS

 enough

0.82

enough

0.67

 Enough

0.61

 ENOUGH

0.61

Enough

0.60

to

0.59

 that

0.58

 estekak

0.53

so

0.51

うち

0.49

Activations Density 0.227%

phrases indicating prioritization or significance in decision-making contexts

No Comments

No Known Activations