INDEX

Explanations

references to specific roles or positions within narratives, particularly focusing on individuals involved in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

StandardCharsets

-0.68

 shrug

-0.63

provincia

-0.63

 direta

-0.63

 scones

-0.62

 shru

-0.61

 Sonne

-0.60

 Kira

-0.60

 мәкалә

-0.59

onomies

-0.58

POSITIVE LOGITS

jLabel

0.88

zy

0.86

eng

0.76

ij

0.74

KommentareTeilen

0.71

burg

0.70

 jLabel

0.69

ping

0.66

TintMode

0.61

 jury

0.60

Activations Density 0.078%

references to specific roles or positions within narratives, particularly focusing on individuals involved in a context

No Comments

No Known Activations