INDEX

Explanations

phrases indicating associations and relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

μ

-0.66

ginx

-0.65

 latine

-0.65

 Wylie

-0.64

dymyr

-0.63

dak

-0.63

 tecn

-0.62

 dover

-0.61

 alpina

-0.60

 Fleur

-0.60

POSITIVE LOGITS

 associates

1.97

 associate

1.96

 association

1.88

 assoc

1.88

 associations

1.86

 associated

1.85

 associ

1.84

 Associated

1.82

 associating

1.81

associated

1.80

Activations Density 0.095%

phrases indicating associations and relationships

No Comments

No Known Activations