INDEX

Explanations

descriptions of physical appearance, particularly related to hair attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

MessageOf

-0.87

 JpaRepository

-0.83

 GetEnumerator

-0.78

jsii

-0.78

 дописавши

-0.75

 ujednoznacz

-0.75

 <>",

-0.75

IsContent

-0.75

 Мексичка

-0.75

WriteBarrier

-0.74

POSITIVE LOGITS

 hairs

0.59

Reg

0.52

 hair

0.51

hair

0.50

毛

0.49

reg

0.48

Reg

0.48

✭✭

0.46

hairs

0.45

ь

0.45

Activations Density 0.252%

descriptions of physical appearance, particularly related to hair attributes

No Comments

No Known Activations