INDEX

Explanations

words related to diplomatic assignments in Afghanistan

oai_token-act-pair · gpt-3.5-turbo

instances of the special character "Ŀ"

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

IFrame

Link

Negative Logits

 imperson

-0.78

 likeness

-0.77

 casing

-0.77

 contact

-0.75

 injured

-0.73

 enhancement

-0.73

undown

-0.71

 intention

-0.70

 cloning

-0.70

 contacts

-0.70

POSITIVE LOGITS

ttp

0.95

said

0.92

catentry

0.88

ï¸ı

0.87

 Ibid

0.87

quickShipAvailable

0.87

Compare

0.85

ï¸

0.84

Â¯

0.81

İ

0.80

Activations Density 0.139%

words related to diplomatic assignments in Afghanistan

instances of the special character "Ŀ"

No Known Activations