INDEX

Explanations

news-related phrases mentioning locations and events

oai_token-act-pair · gpt-3.5-turbo

phrases that contain commas, indicating lists or sequences

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

,—

-0.69

¬¼

-0.67

aur

-0.63

 incom

-0.60

Spec

-0.58

Unt

-0.57

sylv

-0.56

ole

-0.56

).[

-0.56

agine

-0.56

POSITIVE LOGITS

huh

1.10

 meanwhile

1.06

 however

0.95

eh

0.85

 including

0.81

 though

0.81

 albeit

0.78

 according

0.76

aka

0.74

 although

0.73

Activations Density 0.874%

news-related phrases mentioning locations and events

phrases that contain commas, indicating lists or sequences

No Comments

No Known Activations