INDEX

Explanations

terms related to annual reports and statistics

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.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

WriteLiteral

-0.68

 Spock

-0.57

 puck

-0.56

énario

-0.54

 schö

-0.54

 lavander

-0.54

\&

-0.53

mb

-0.53

 وتسجيلات

-0.53

 SPDX

-0.52

POSITIVE LOGITS

 annual

1.36

ANNUAL

1.35

annual

1.26

 yearly

1.23

 annuel

1.21

Annual

1.20

 Annual

1.20

 ANNUAL

1.16

 anual

1.11

 annually

1.10

Activations Density 0.020%

terms related to annual reports and statistics

No Comments

No Known Activations