INDEX

Explanations

references to research and studies in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

NameInMap

-0.93

odil

-0.75

InMillis

-0.70

 Clegg

-0.70

IBarButtonItem

-0.69

eclamp

-0.68

PendingIntent

-0.67

 GeoNames

-0.67

 signatory

-0.67

PageModule

-0.65

POSITIVE LOGITS

 research

0.94

RESEARCH

0.90

 Research

0.85

research

0.84

Research

0.81

 researches

0.79

 researchers

0.79

 RESEARCH

0.75

Pesquisa

0.75

 Investigación

0.74

Activations Density 0.065%

references to research and studies in various contexts

No Comments

No Known Activations