INDEX

Explanations

dates mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

parentheses in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 langu

-0.78

 discrim

-0.72

 asteroids

-0.70

 altogether

-0.69

 increment

-0.65

 unsett

-0.65

 attacker

-0.65

 skyrocket

-0.65

 onward

-0.65

 adversary

-0.65

POSITIVE LOGITS

Photo

1.52

Courtesy

1.37

photo

1.25

Credit

1.25

credit

1.25

Picture

1.07

Reuters

1.06

Screenshot

1.06

 PHOTO

1.04

 Courtesy

1.04

Activations Density 0.057%

dates mentioned in news articles

parentheses in the text

No Comments

No Known Activations