INDEX

Explanations

references to previous content or mentions within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ividual

-0.66

ypress

-0.65

EXPERIMENTAL

-0.64

UIControlState

-0.64

expandindo

-0.64

prnewswire

-0.63

Xna

-0.63

ArrowToggle

-0.61

яг

-0.60

%")

-0.60

POSITIVE LOGITS

 refer

1.47

 referencing

1.39

 references

1.38

 referring

1.35

 reference

1.25

 referred

1.22

 referenced

1.20

 refers

1.19

 Referring

1.18

 Refer

1.17

Activations Density 0.228%

references to previous content or mentions within the text

No Comments

No Known Activations