INDEX

Explanations

terms related to partnerships and affiliations

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

Yag

-0.76

 fatig

-0.75

Hockey

-0.74

 Scin

-0.72

srs

-0.70

Eul

-0.69

 millionaires

-0.68

 Pompeo

-0.68

 Hockey

-0.67

IAC

-0.67

POSITIVE LOGITS

 partners

2.51

 partner

2.43

 Partner

2.31

 Partners

2.28

partners

2.25

Partners

2.20

Partner

2.19

partner

2.18

 PARTNER

2.11

 PARTNERS

2.01

Activations Density 0.035%

terms related to partnerships and affiliations

No Comments

No Known Activations