INDEX

Explanations

proper nouns starting or containing "Wil" with varying activation for different patterns

oai_token-act-pair · gpt-3.5-turbo

variations of the name "Wilbur" and associated names

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

zona

-0.80

-0.73

drm

-0.70

uctive

-0.70

UID

-0.69

ccording

-0.69

htaking

-0.67

hiba

-0.67

è¦ļéĨĴ

-0.66

MAT

-0.66

POSITIVE LOGITS

stad

0.95

 Webb

0.90

fleet

0.75

beck

0.72

 Howell

0.69

 Anderson

0.68

burg

0.68

 Clark

0.68

 Weld

0.67

 Wales

0.66

Activations Density 0.106%

proper nouns starting or containing "Wil" with varying activation for different patterns

variations of the name "Wilbur" and associated names

No Comments

No Known Activations