INDEX

Explanations

words related to specific locations or names, especially with the pattern "Br..." and "im"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Br" followed by various letter combinations indicative of names or places

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

IFrame

Link

Negative Logits

ĸļ

-0.89

©¶æ

-0.72

 Reincarn

-0.64

 seiz

-0.63

 Uriel

-0.61

rogens

-0.61

 thor

-0.60

 Shutterstock

-0.59

 nitrogen

-0.57

 Gujar

-0.57

POSITIVE LOGITS

sels

0.98

swick

0.94

itte

0.93

gger

0.89

zinski

0.87

illet

0.85

wine

0.83

veland

0.82

Ã§a

0.79

mingham

0.79

Activations Density 0.078%

words related to specific locations or names, especially with the pattern "Br..." and "im"

instances of the word "Br" followed by various letter combinations indicative of names or places

No Known Activations