INDEX

Explanations

phrases related to expectations or obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

تقاوى

-0.95

ftagPool

-0.95

 nakalista

-0.93

 InputDecoration

-0.92

 BoxDecoration

-0.92

ViewFeatures

-0.92

 հղումներ

-0.91

 AssemblyCulture

-0.89

 JpaRepository

-0.84

ImageContext

-0.81

POSITIVE LOGITS

 supposed

1.00

be

0.84

supposed

0.76

 should

0.74

 shall

0.68

 doveva

0.63

 moet

0.63

 Should

0.61

 soll

0.61

 debe

0.60

Activations Density 0.113%

phrases related to expectations or obligations

No Comments

No Known Activations