INDEX

Explanations

references to reading and textual consumption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

awtextra

-0.92

 bezeichneter

-0.88

berdayakan

-0.85

 MonoBehaviour

-0.84

wpi

-0.81

Diweddarwch

-0.79

 Wayback

-0.77

 createSprite

-0.76

djangoproject

-0.75

Sucesor

-0.75

POSITIVE LOGITS

 reading

1.36

 read

1.31

 reads

1.26

Reading

1.12

 Reading

1.10

reading

1.03

read

1.00

 lezen

0.98

읽

0.97

 reread

0.96

Activations Density 0.153%

references to reading and textual consumption

No Comments

No Known Activations