INDEX

Explanations

references to geographical regions or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 næste

-0.48

 køb

-0.46

læg

-0.45

 række

-0.44

 måned

-0.44

 mulighed

-0.43

gatan

-0.43

 dager

-0.43

gnings

-0.42

чь

-0.42

POSITIVE LOGITS

 Norway

0.98

 Norwegian

0.97

 Norwe

0.90

 fjord

0.85

 Trondheim

0.84

 norvég

0.83

 Oslo

0.82

Norwegian

0.82

Norway

0.81

 Norvège

0.80

Activations Density 0.129%

references to geographical regions or locations

No Comments

No Known Activations