INDEX

Explanations

terms related to quantifying or measuring something, particularly in a scientific or technical context

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

">//

-0.59



-0.57

 بيها

-0.55

 ſind

-0.54

 ſont

-0.52

：“……”

-0.51

 leaſt

-0.51

AxisAlignment

-0.51

 Shotgun

-0.51

PMailer

-0.51

POSITIVE LOGITS

 stops

0.50

 stop

0.44

stopped

0.41

stop

0.41

Stops

0.40

stops

0.40

 stopped

0.38

Stop

0.37

STOP

0.35

 reaches

0.35

Activations Density 0.185%

terms related to quantifying or measuring something, particularly in a scientific or technical context

No Comments

No Known Activations