INDEX

Explanations

references to historical figures and events

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Majefty

-0.57

ucoup

-0.51

 Tanger

-0.47

 shel

-0.45

lobal

-0.45

 فريبيس

-0.45

neſs

-0.45

 Thess

-0.45

 sliders

-0.45

 reducers

-0.44

POSITIVE LOGITS

tonode

0.57

 كومونز

0.41

 garçons

0.41

 muhte

0.39

WriteTagHelper

0.39

 生命周期

0.39

 apparently

0.37

 survie

0.36

 varones

0.36

 feroit

0.36

Activations Density 0.072%

references to historical figures and events

No Comments

No Known Activations