INDEX

Explanations

lists and references to various items or services

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

harapkan

-0.40

travail

-0.39

 CGPoint

-0.37

 Appellant

-0.36

scheduled

-0.35

 tarko

-0.35

 przeznac

-0.35

 isComment

-0.35

 Umgang

-0.35

 Unterricht

-0.34

POSITIVE LOGITS

 list

0.79

 lista

0.63

list

0.61

清单

0.60

 countless

0.60

 Lijst

0.60

 Liste

0.59

 liste

0.59

 listing

0.59

rungsseite

0.58

Activations Density 0.016%

lists and references to various items or services

No Comments

No Known Activations