INDEX

Explanations

words related to personal opinions and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

INSEE

-0.65

 Hamlin

-0.61

 menti

-0.61

 Drapeau

-0.60

 Mela

-0.60

kém

-0.59

rsiniz

-0.59

м

-0.55

 "..\..\

-0.55

okovic

-0.55

POSITIVE LOGITS

 been

1.21

 تانيه

1.20

 للمعارف

0.95

 gotta

0.92

been

0.89

󠁿

0.88

)’

0.84

 gonna

0.83

got

0.80

itudinal

0.80

Activations Density 0.251%

words related to personal opinions and evaluations

No Comments

No Known Activations