INDEX

Explanations

verbs indicating change or progress

oai_token-act-pair · gpt-3.5-turbo

verbs and phrases indicating growth or change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Sphere

-0.72

 arri

-0.69

viz

-0.69

»Ĵ

-0.66

 Brit

-0.63

esides

-0.63

Suc

-0.63

Sud

-0.62

 Princ

-0.62

Tac

-0.61

POSITIVE LOGITS

owship

0.75

ilial

0.71

pend

0.70

 parity

0.68

daq

0.67

ulate

0.67

leground

0.65

 defenses

0.65

nell

0.64

leep

0.64

Activations Density 0.210%

verbs indicating change or progress

verbs and phrases indicating growth or change

No Comments

No Known Activations