INDEX

Explanations

indicators of statistical significance or notable events

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

is

-0.56

“

-0.56

itemize

-0.55

Ref

-0.54

-0.53

-0.52

蜀

-0.51

we

-0.50

POSITIVE LOGITS

Rüyada

1.15

 myſelf

1.05

rungsseite

1.04

ⓧ

1.02

 useHistory

1.01



1.00

 fufficient

0.99

 themſelves

0.98

StoreMessageInfo

0.98

 himſelf

0.97

Activations Density 0.040%

indicators of statistical significance or notable events

No Comments

No Known Activations