INDEX

Explanations

references to living experiences 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

 rasch

-0.72

jsonwebtoken

-0.68

erequisite

-0.66

 esboço

-0.65

 Koenig

-0.63

Steffen

-0.63

 collègues

-0.63

 nonatomic

-0.62

authToken

-0.62

 entrants

-0.61

POSITIVE LOGITS

 lived

2.02

 living

1.94

 Lived

1.65

 live

1.59

living

1.56

 Living

1.56

Living

1.54

lived

1.44

 LIVING

1.44

 vivir

1.43

Activations Density 0.057%

references to living experiences or situations

No Comments

No Known Activations