INDEX

Explanations

expressions related to personal beliefs and reflections on experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Occasionally

-0.75

 Slightly

-0.72

 Occasionally

-0.70

SOME

-0.69

 occasionally

-0.69

Slightly

-0.68

somewhere

-0.68

slightly

-0.66

Vidite

-0.66

 tantôt

-0.64

POSITIVE LOGITS

 much

1.92

too

1.51

much

1.50

Much

1.34

 Much

1.28

 muito

1.22

 many

1.22

TOO

1.21

too

1.21

 allzu

1.15

Activations Density 0.330%

expressions related to personal beliefs and reflections on experiences

No Comments

No Known Activations