INDEX

Explanations

conditional phrases indicating hypothetical scenarios or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 pleaſure

-0.70

berton

-0.68

 Portail

-0.67

 Palacios

-0.66

 Jefus

-0.65

 sqlSession

-0.63

çalves

-0.62

wardship

-0.61

беріга

-0.61

amaño

-0.61

POSITIVE LOGITS

 jakby

0.89

 seolah

0.85

 будто

0.80

Personensuche

0.73

 gdyby

0.70

 صوتيه

0.69

رشف

0.69

彿

0.68

 словно

0.68

InSection

0.65

Activations Density 0.059%

conditional phrases indicating hypothetical scenarios or situations

No Comments

No Known Activations