INDEX

Explanations

phrases that express comparisons and similarities between experiences or concepts

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

mability

-0.67

Джерела

-0.59

明明

-0.57

 fubject

-0.57

 purpoſe

-0.57

 Silla

-0.56

Enllaços

-0.55

 diſt

-0.55

tetten

-0.55

losis

-0.55

POSITIVE LOGITS

 like

0.76

enumii

0.72

 Like

0.65

like

0.64

Like

0.63

 kuten

0.59

 seperti

0.58

 giống

0.57

 LIKE

0.57

 kuin

0.57

Activations Density 0.520%

phrases that express comparisons and similarities between experiences or concepts

No Comments

No Known Activations