INDEX

Explanations

comparative adjectives and phrases indicating levels or differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 nourrir

-0.58

 edades

-0.52

fæ

-0.52

 esso

-0.52

 venait

-0.51

 graça

-0.51

szak

-0.51

 másik

-0.50

 manhã

-0.50

 gió

-0.49

POSITIVE LOGITS

AddTagHelper

0.93

 increase

0.92

HasForeignKey

0.91

 high

0.84

UnusedPrivate

0.84

 higher

0.83

 amount

0.83

 highest

0.83

increase

0.81

 increases

0.80

Activations Density 0.822%

comparative adjectives and phrases indicating levels or differences

No Comments

No Known Activations