INDEX

Explanations

numeric values stated as words

oai_token-act-pair · gpt-3.5-turbo

specific numerical values and their associations within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

osaurs

-0.47

 favor

-0.43

pres

-0.43

î

-0.41

éĸ

-0.39

 rocket

-0.39

kj

-0.39

ildo

-0.38

minecraft

-0.38

LOS

-0.38

POSITIVE LOGITS

etheless

0.67

 tradem

0.61

awaru

0.60

rul

0.59

 corrid

0.57

 destro

0.56

DragonMagazine

0.55

theless

0.55

 skelet

0.54

 challeng

0.53

Activations Density 1.972%

numeric values stated as words

specific numerical values and their associations within various contexts

No Comments

No Known Activations