INDEX

Explanations

words related to "implication" and "impact."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.71

 Lagu

-0.64

yarnpkg

-0.59

 tartalomajánló

-0.59

 gynhyrchwyd

-0.58

 schme

-0.58

$_['

-0.57

省市镇

-0.57

antası

-0.56

Kilder

-0.56

POSITIVE LOGITS

 Cæsar

0.84

Imp

0.84

IMP

0.79

Imp

0.78

 itſelf

0.76

 myſelf

0.70

 leaſt

0.69

 Monfieur

0.67

*/;

0.65

 becauſe

0.64

Activations Density 0.126%

words related to "implication" and "impact."

No Comments

No Known Activations