INDEX

Explanations

qualifiers and conditional phrases that indicate uncertainty or limitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

\{\\

-0.81

actionMode

-0.78

󠁢

-0.76

 ddelweddau

-0.75

 actionMode

-0.66

StoryboardSegue

-0.66

idão

-0.64

 Pingback

-0.61

 Вікі

-0.60

ArrowToggle

-0.60

POSITIVE LOGITS

but

0.46

invokeLater

0.45

 centrum

0.45

 generally

0.44

 algemeen

0.42

 lignes

0.42

 ağı

0.42

 izvē

0.41

Certain

0.41

 snippetHide

0.40

Activations Density 0.251%

qualifiers and conditional phrases that indicate uncertainty or limitation

No Comments

No Known Activations