INDEX

Explanations

indicators of significant concepts or themes in text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.60

-0.57

-0.56

-0.54

-0.53

-0.52

-0.51

POSITIVE LOGITS

rungsseite

1.22

CloseOperation

1.00

 فريبيس

1.00

 الحره

0.99

 pinulongan

0.90

sizeCache

0.90

 beginnetje

0.89

出版年

0.89

ftagPool

0.88

 defaultstate

0.88

Activations Density 0.018%

indicators of significant concepts or themes in text

No Comments

No Known Activations