INDEX

Explanations

mentions of locations and geographic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 мәкалә

-0.54

 estekak

-0.53

viembre

-0.53

ParallelGroup

-0.52

 ISLANDS

-0.50

engertian

-0.50

НЫХ

-0.49

}(),

-0.49

:])

-0.48

 Dubrovnik

-0.45

POSITIVE LOGITS

 штат

0.78

 near

0.77

 where

0.72

PyExc

0.66

near

0.65

 Illinois

0.65

 United

0.65

 Texas

0.64

where

0.63

 Calif

0.62

Activations Density 0.208%

mentions of locations and geographic contexts

No Comments

No Known Activations