INDEX

Explanations

references to hair

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ViewFeatures

-0.78

gridx

-0.74

omitempty

-0.71

setHorizontal

-0.70

:+:

-0.69

mybatisplus

-0.67

EDEFAULT

-0.67

::_('

-0.67

 Winfrey

-0.66

SQLiteDatabase

-0.65

POSITIVE LOGITS

hair

1.27

 hair

1.26

Hair

1.19

 Hair

1.12

HAIR

1.00

 HAIR

0.99

 hairs

0.98

haired

0.79

hairs

0.79

 cabelo

0.76

Activations Density 0.591%

references to hair

No Comments

No Known Activations