INDEX

Explanations

specific scientific and technical terms related to research and methodologies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelf

-0.94

 Мексичка

-0.92

 myſelf

-0.91

出版年

-0.89

 EconPapers

-0.86

 ویکی‌پدیا

-0.85

 الرياضيه

-0.85

 Roskov

-0.83

ConstraintMaker

-0.82

 ſind

-0.82

POSITIVE LOGITS

0.74

0.61

0.56

ればいい

0.52

0.49

ってみる

0.49

0.47

ണം

0.45

zonego

0.45

Activations Density 5.375%

specific scientific and technical terms related to research and methodologies

No Comments

No Known Activations