INDEX

Explanations

mentions of showers or related activities

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

Litt

-0.67

 Litt

-0.62

ⓧ

-0.61

zs

-0.60

 Sinha

-0.60

tyg

-0.60

kon

-0.59

 edad

-0.59

ontent

-0.59

 Sack

-0.59

POSITIVE LOGITS

 shower

2.31

 Shower

2.17

 showers

2.05

shower

2.00

Shower

1.98

 Showers

1.96

 showering

1.63

 showered

1.52

 Dusche

1.35

 doccia

1.18

Activations Density 0.044%

mentions of showers or related activities

No Comments

No Known Activations