INDEX

Explanations

expressions indicating perception or description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

})));

-0.73

 kasarigan

-0.67

 SEDS

-0.64

yntaxException

-0.63

 stead

-0.62

 Devine

-0.62

SPATH

-0.61

bary

-0.60

httphttps

-0.59

 Stabilization

-0.57

POSITIVE LOGITS

视为

0.59

 varandra

0.58

 soyez

0.58

 Baran

0.56

 becoming

0.56

writerow

0.55

 konusu

0.55

 sonno

0.55

 being

0.54

beln

0.54

Activations Density 0.313%

expressions indicating perception or description

No Comments

No Known Activations