INDEX

Explanations

positive descriptors and adjectives that indicate quality or value

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

 émotion

-0.66

mga

-0.65

 signatures

-0.63

itemBuilder

-0.61

 deficiencies

-0.59

 honte

-0.58

 these

-0.57

 tasche

-0.57

paravant

-0.57

ForAll

-0.57

POSITIVE LOGITS

__*/

0.85

'{@

0.82

0.80

FXML

0.79

 IBOutlet

0.79

typeorm

0.77

dafx

0.73

parsedMessage

0.73

PerformLayout

0.71

 }}"></

0.69

Activations Density 0.459%

positive descriptors and adjectives that indicate quality or value

No Comments

No Known Activations