INDEX

Explanations

references to medical or scientific terms related to health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

SPC

-0.48

ace

-0.43

ACE

-0.41

 أيضًا

-0.39

 klin

-0.38

DAE

-0.38

ิ้ง

-0.38

 Condor

-0.38

XXV

-0.37

 userSchema

-0.37

POSITIVE LOGITS

ValueStyle

0.86

évaluateur

0.82

OGND

0.79

 SafeMath

0.73

httphttps

0.73

<bos>

0.72

IndentedString

0.72

存于互联网档案馆

0.68

IsContent

0.67

AccessorTable

0.66

Activations Density 0.857%

references to medical or scientific terms related to health conditions

No Comments

No Known Activations