INDEX

Explanations

references to "Hell" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 بيها

-0.76

werp

-0.69

 للاسماء

-0.68

 typelib

-0.67

書館

-0.66

 دیکھیے

-0.66

ogna

-0.65

acyjna

-0.65

 Goya

-0.65

icoot

-0.63

POSITIVE LOGITS

hells

0.63

Hel

0.62

hel

0.59

 HELL

0.58

MLLoader

0.56

 Helle

0.51

 Hell

0.50

HEL

0.49

 Helene

0.49

Hel

0.49

Activations Density 0.060%

references to "Hell" and related terms

No Comments

No Known Activations