INDEX

Explanations

expressions of gratitude and encouragement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.77

 kasarigan

-0.75

 Houſe

-0.74

Efq

-0.73

 houſe

-0.73

 فريبيس

-0.71

 Мексичка

-0.67

 Chwiliwch

-0.65

SBATCH

-0.65

Eſ

-0.63

POSITIVE LOGITS

<eos>

0.69

↵↵

0.60

endsection

0.56

RoutingModule

0.51

↵↵↵

0.49

”

0.46

↵↵↵↵↵

0.46

endpush

0.46

crity

0.46

tabular

0.45

Activations Density 0.163%

expressions of gratitude and encouragement

No Comments

No Known Activations