INDEX

Explanations

terminology related to comparisons and standards, particularly in evaluating properties, effectiveness, and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

migrationBuilder

-0.85

 estekak

-0.81

SequentialGroup

-0.75

 propOrder

-0.73

rungsseite

-0.70

DockStyle

-0.69

Biographie

-0.68

 INTERESAR

-0.60

expandindo

-0.59

SOUNDBITE

-0.59

POSITIVE LOGITS

 financially

1.50

 musically

1.42

 physically

1.30

 spiritually

1.28

 economically

1.24

 intellectually

1.21

 psychologically

1.20

 academically

1.18

 Physically

1.16

 politically

1.15

Activations Density 0.828%

terminology related to comparisons and standards, particularly in evaluating properties, effectiveness, and conditions

No Comments

No Known Activations