INDEX

Explanations

references to authors and researchers in scientific publications

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

Pic

-0.25

pic

-0.23

Nem

-0.23

Pic

-0.21

setContentView

-0.21

 Dawes

-0.21

 прокура

-0.21

口的

-0.21

 Spanish

-0.20

POSITIVE LOGITS

="@+

0.79

 فريبيس

0.77

argout

0.77

Autoritní

0.73

تقاوى

0.73

 nakalista

0.70

 ujednoznacz

0.70

 незавершена

0.67

majánló

0.66

 للمعارف

0.65

Activations Density 0.025%

references to authors and researchers in scientific publications

No Comments

No Known Activations