INDEX

Explanations

expressions related to personal opinions 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 houſe

-0.55

Efq

-0.50

 Chriftian

-0.50

 myſelf

-0.49

 Diſ

-0.46

化

-0.46

 vinyle

-0.46

 pleaſure

-0.45

sū

-0.45

 ſhe

-0.45

POSITIVE LOGITS

umably

1.13

 glaube

1.12

 perhaps

1.07

mutlich

1.07

">//

1.06

Probably

0.97

perhaps

0.97

NameInMap

0.96

 probably

0.96

 наверное

0.96

Activations Density 0.132%

expressions related to personal opinions and beliefs

No Comments

No Known Activations