INDEX

Explanations

references to numerical values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 المعيارى

-1.12

 ModelExpression

-1.09

 فريبيس

-1.02

 AssemblyCulture

-1.01

 للمعارف

-0.96

IsMutable

-0.94

 HttpNotFound

-0.94

 '\\;'

-0.93

 مشين

-0.91

 незавершена

-0.90

POSITIVE LOGITS

0.55

<eos>

0.52

ANTO

0.45

0.43

0.42

 cole

0.41

0.40

Int

0.40

 oper

0.39

Ce

0.38

Activations Density 0.599%

references to numerical values and measurements

No Comments

No Known Activations