INDEX

Explanations

references to individuals named Lore

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lore" and variations of the word "lore"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akra

-0.81

ruciating

-0.78

urers

-0.73

uyomi

-0.69

alogue

-0.64

obs

-0.64

undred

-0.64

otos

-0.64

éĹĺ

-0.64

apeshifter

-0.63

POSITIVE LOGITS

nz

1.18

tta

1.11

tto

1.02

gon

1.01

walker

0.93

bolt

0.92

le

0.91

suit

0.91

gate

0.90

 Lore

0.90

Activations Density 0.024%

references to individuals named Lore

mentions of the name "Lore" and variations of the word "lore"

No Comments

No Known Activations