INDEX

Explanations

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ViewFeatures

-0.83

+#+#

-0.80

IonicModule

-0.79

 NgModule

-0.78

TypedDataSet

-0.76

DebuggerNonUser

-0.75

RTEE

-0.74

PreferredItem

-0.73

 Vele

-0.72

 nonatomic

-0.71

POSITIVE LOGITS

 THANKS

1.02

THANKS

0.92

 thanks

0.90

 Thanks

0.88

Thanks

0.85

thanks

0.80

 Schon

0.78

Schon

0.78

равда

0.76

 refs

0.74

Activations Density 0.047%

expressions of gratitude

No Comments

No Known Activations