INDEX

Explanations

terms related to specific measurements and statistical data

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

 Anſ

-0.77

Efq

-0.77

 للاسماء

-0.77

oredCriteria

-0.74

 Monfieur

-0.74

 myſelf

-0.73

-0.72

-/

-0.70

\&

-0.70

 himſelf

-0.70

POSITIVE LOGITS

uxxxx

0.66

DoubleQuotes

0.53

Démographie

0.52

 CreateTagHelper

0.47

脚注の使い方

0.46

makeConstraints

0.46

recated

0.46

 uska

0.45

aus

0.44

Demografie

0.44

Activations Density 1.193%

terms related to specific measurements and statistical data

No Comments

No Known Activations