INDEX

Explanations

references to hair and its characteristics, including loss or thickness

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

"hair."

np_acts-logits-general · gemini-2.0-flash

hair quantity and properties

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 EconPapers

-0.84

 مشين

-0.76

hashtags

-0.76

CppMethod

-0.74

WriteTagHelper

-0.72

ypeł

-0.71

}),

-0.68

 виправивши

-0.68

niosek

-0.68

}());

-0.67

POSITIVE LOGITS

 follicles

0.69

 follicle

0.68

dressing

0.67

DRESS

0.60

dress

0.58

IContainer

0.58

 HAIR

0.56

 Hair

0.55

less

0.55

HAIR

0.55

Activations Density 0.079%

references to hair and its characteristics, including loss or thickness

"hair."

hair quantity and properties

No Comments

No Known Activations