INDEX

Explanations

instances of the word "apply" and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 незавершена

-1.05

تقاوى

-0.98

 يتيمه

-0.92

بوابة

-0.91

 فريبيس

-0.86

SourceChecksum

-0.84

abestanden

-0.83

+#+#

-0.78

BeginContext

-0.77

ctose

-0.77

POSITIVE LOGITS

 APPLY

1.46

 Apply

1.44

Apply

1.40

Applied

1.40

 Applied

1.38

 applied

1.34

apply

1.34

 apply

1.33

applied

1.32

APPLY

1.30

Activations Density 0.117%

instances of the word "apply" and its various forms

No Comments

No Known Activations