INDEX

Explanations

terms related to resistance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

the

-0.55

al

-0.52

ichen

-0.52

mar

-0.51

ate

-0.50

he

-0.50

↵↵

-0.50

 majority

-0.50

 bater

-0.50

POSITIVE LOGITS

Efq

1.43

 itſelf

1.32

 Jefus

1.30

 myſelf

1.24

 Majefty

1.18

ſelf

1.18

 Theſe

1.13

 poffible

1.13

 auffi

1.12

 purpoſe

1.12

Activations Density 0.104%

terms related to resistance in various contexts

No Comments

No Known Activations