INDEX

Explanations

instances of the word "None."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 poussière

-0.67

 buhay

-0.65

 treasure

-0.65

ward

-0.64

 Knud

-0.63

########.

-0.62

 Espacio

-0.61

ilo

-0.61

 Maggio

-0.61

Spiral

-0.61

POSITIVE LOGITS

 none

1.25

none

1.18

None

1.14

NONE

1.13

 None

1.10

 NONE

1.09

 ninguno

0.96

InputBorder

0.90

+#+

0.89

Nih

0.80

Activations Density 0.086%

instances of the word "None."

No Comments

No Known Activations