INDEX

Explanations

expressions indicating quality or superiority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ViewFeatures

-1.14

Geografie

-0.75

 Drapeau

-0.74

transQ

-0.72

weile

-0.71

DockStyle

-0.71

ęku

-0.71

Linki

-0.71

yntaxException

-0.69

BIOGRAPHY

-0.68

POSITIVE LOGITS

 BEST

1.61

BEST

1.58

best

1.51

Best

1.46

 best

1.44

 Best

1.44

melhor

1.18

better

1.12

 beſt

1.10

 BETTER

1.07

Activations Density 0.060%

expressions indicating quality or superiority

No Comments

No Known Activations