INDEX

Explanations

phrases indicating the importance or significance of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 myſelf

-0.79

 raiſ

-0.72

XmlAccessorType

-0.71

 ſtate

-0.70

Disadvantages

-0.69

 themſelves

-0.69

 itſelf

-0.68

 Reſ

-0.68

 елның

-0.68

 ſtre

-0.67

POSITIVE LOGITS

no

1.00

 unsur

0.98

 fitting

0.83

no

0.78

fitting

0.77

 Fitting

0.73

 naturally

0.71

 Kein

0.69

 logical

0.69

 understandable

0.67

Activations Density 0.255%

phrases indicating the importance or significance of something

No Comments

No Known Activations