INDEX

Explanations

adjectives that convey positive qualities or capabilities

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

adjective as

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

httphttps

-0.73

contentLoaded

-0.61

 kaarangay

-0.56

 ErrIntOverflow

-0.55

 ſei

-0.52

]")]

-0.50

 beſte

-0.50

 faſt

-0.50

 المعيارى

-0.50

újo

-0.49

POSITIVE LOGITS

as

2.16

 sebagai

1.09

 как

1.09

 kuin

1.09

 як

1.03

 quanto

0.95

 như

0.92

 както

0.85

 كما

0.82

 Sebagai

0.79

Activations Density 0.109%

adjectives that convey positive qualities or capabilities

adjective as

No Comments

No Known Activations