INDEX

Explanations

references to levels or positions in a hierarchical structure, particularly the word "above."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Portail

-0.75

 Gilles

-0.65

man

-0.60

 kasarigan

-0.59

riwal

-0.58

 cuales

-0.58

?")

-0.57

cal

-0.57

😭😭

-0.57

 akal

-0.56

POSITIVE LOGITS

 ABOVE

1.54

ABOVE

1.53

 Above

1.36

Above

1.31

above

1.29

 BELOW

1.22

 above

1.21

bove

1.20

 Boven

1.14

 Below

1.02

Activations Density 0.123%

references to levels or positions in a hierarchical structure, particularly the word "above."

No Comments

No Known Activations