INDEX

Explanations

phrases indicating past experiences or regrets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

IndexOutOfBounds

-0.61

detectChanges

-0.58

Ames

-0.56

parsedMessage

-0.56

 DialogInterface

-0.54

목

-0.53

 Somme

-0.53

kij

-0.53

 useRef

-0.53

Liên

-0.52

POSITIVE LOGITS

 would

1.19

 WOULD

1.12

would

1.09

 Would

1.05

Would

1.05

 wouldn

0.91

 Wouldn

0.85

 gdyby

0.83

wouldn

0.80

 wäre

0.79

Activations Density 0.255%

phrases indicating past experiences or regrets

No Comments

No Known Activations