INDEX

Explanations

phrases indicating realization or acknowledgment of thoughts and beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Houſe

-0.58

 Majefty

-0.58

 ddelweddau

-0.56

 Acerca

-0.56

ſelf

-0.55

 Schengen

-0.55

 Shakspeare

-0.54

herself

-0.54

 Himself

-0.54

 avengers

-0.53

POSITIVE LOGITS

 they

2.01

we

1.84

 there

1.68

it

1.60

he

1.46

you

1.30

she

1.20

 они

1.04

they

0.97

the

0.94

Activations Density 0.525%

phrases indicating realization or acknowledgment of thoughts and beliefs

No Comments

No Known Activations