INDEX

Explanations

words and phrases related to questions and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

huu

-0.65

סים

-0.64

 Persönlichkeit

-0.61

block

-0.59

 său

-0.58

کور

-0.57

 faune

-0.57

 simplu

-0.56

 centavos

-0.55

tă

-0.55

POSITIVE LOGITS

 herself

1.27

 shes

1.08

annica

0.98

 которая

0.98

 która

0.96

 která

0.96

 ihrer

0.95

herself

0.94

 goddess

0.87

 Latina

0.86

Activations Density 0.088%

words and phrases related to questions and inquiries

No Comments

No Known Activations