INDEX

Explanations

mentions of the term "eng" or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.57

-0.55

-0.54

-0.53

-0.52

in

-0.51

-0.50

POSITIVE LOGITS

Efq

0.94

 illuminating

0.93

脚注の使い方

0.92

 myſelf

0.90

ReusableCell

0.88

 engaging

0.86

 سكانية

0.85

 EconPapers

0.84

存于互联网档案馆

0.83

 illuminates

0.83

Activations Density 0.137%

mentions of the term "eng" or related concepts

No Comments

No Known Activations