INDEX

Explanations

negative sentiments or actions in a legal or regulatory context

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

 Monfieur

-0.90

ness

-0.87

lask

-0.74

ings

-0.74

 itſelf

-0.74

ling

-0.73

arrêt

-0.72

 Valentín

-0.71

 jesús

-0.71

ting

-0.68

POSITIVE LOGITS

parsedMessage

0.92

 lancar

0.70

aero

0.70

χρι

0.69

tershire

0.62

oca

0.61

пети

0.61

eating

0.59

 Dooley

0.58

Activations Density 0.361%

negative sentiments or actions in a legal or regulatory context

No Comments

No Known Activations