INDEX

Explanations

occurrences of the term "goog," indicating a focus on Google-related content or references

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

IsMutable

-0.81

initely

-0.68

AppMethodBeat

-0.63

ofition

-0.63

ⅰ

-0.62

ViewImports

-0.61

={`${

-0.61

bcryptjs

-0.60

Seznam

-0.60

 ويكيميديا

-0.60

POSITIVE LOGITS

USP

1.39

ParallelGroup

1.37

rungsseite

1.08

허

0.96

BeginContext

0.95

USP

0.92

Hozzáférés

0.87

Tembelea

0.86

NOI

0.85

enumi

0.83

Activations Density 0.003%

occurrences of the term "goog," indicating a focus on Google-related content or references

No Comments

No Known Activations