INDEX

Explanations

specific adjectives describing items or experiences

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

そこは

-0.69

 portanto

-0.66

SourceChecksum

-0.63

otherwise

-0.62

 Therefore

-0.60

seamnă

-0.60

 Otherwise

-0.59

التالي

-0.58

Otherwise

-0.58

ご了承ください

-0.57

POSITIVE LOGITS

 especially

1.19

Especially

1.14

especially

1.12

 Especially

1.04

 Особенно

1.00

 особенно

0.89

 particularly

0.89

собенно

0.88

 ESPEC

0.88

particularly

0.83

Activations Density 0.111%

specific adjectives describing items or experiences

No Comments

No Known Activations