INDEX

Explanations

occurrences of coding or programming terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 fueran

-0.52

Be

-0.51

 were

-0.51

 weren

-0.51

相

-0.49

-0.47

POSITIVE LOGITS

rungsseite

1.13

 itſelf

1.08

expandindo

1.00

Diweddarwch

0.99

 transmits

0.99

 insuffisamment

0.95

ibrator

0.95

Hochspringen

0.94

 كومونز

0.93

 himſelf

0.92

Activations Density 0.064%

occurrences of coding or programming terminology

No Comments

No Known Activations