INDEX

Explanations

programming-related syntax and language constructs

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

Autoritní

-0.63

ſelf

-0.55

évaluateur

-0.54

 pleaſure

-0.54

 ProtoMessage

-0.52

 onAnimation

-0.50

 themſelves

-0.50

 kasarigan

-0.49

 Monfieur

-0.48

ViewImports

-0.47

POSITIVE LOGITS

 soup

1.28

 Soup

1.17

soup

1.16

Soup

1.05

 BeautifulSoup

1.04

 soups

0.85

SOU

0.85

 broth

0.72

 sopa

0.71

SOU

0.69

Activations Density 0.005%

programming-related syntax and language constructs

No Comments

No Known Activations