INDEX

Explanations

professionals or individuals by their titles or roles

oai_token-act-pair · gpt-3.5-turbo

references to individuals introduced with "who."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Anything

-0.67

 Dominion

-0.67

 Federation

-0.66

ÂłÂłÂłÂł

-0.66

 VIDEOS

-0.61

 Guys

-0.59

 Delicious

-0.59

 Bound

-0.59

 drying

-0.57

ãĤª

-0.57

POSITIVE LOGITS

 frequ

1.05

 specializes

1.03

 accompanies

1.03

 oversaw

1.01

 resided

1.00

 preceded

0.99

 attends

0.98

 attended

0.96

 lived

0.92

 accompanied

0.92

Activations Density 0.141%

professionals or individuals by their titles or roles

references to individuals introduced with "who."

No Known Activations