INDEX

Explanations

references to opinions and subjective viewpoints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

--;

-0.69

 eryth

-0.68

>';

-0.68

 бла

-0.68

 essenziale

-0.66

'',

-0.66

 fameux

-0.65

endish

-0.65

ddy

-0.65

benar

-0.64

POSITIVE LOGITS

 opinion

2.49

 Opinion

2.30

opinion

2.25

 opinions

2.25

Opinion

2.07

 Opinions

2.06

 OPINION

1.96

opinions

1.90

Opinions

1.77

 Opin

1.75

Activations Density 0.080%

references to opinions and subjective viewpoints

No Comments

No Known Activations