INDEX

Explanations

mentions of the term "Lo."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lo" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

manship

-0.93

*/(

-0.78

ãĤ¼ãĤ¦ãĤ¹

-0.78

sonian

-0.77

ãĥĩ

-0.75

itated

-0.75

rations

-0.74

ãĥ¼ãĥĨãĤ£

-0.74

rity

-0.72

nai

-0.72

POSITIVE LOGITS

zzle

1.08

veland

1.08

zzi

1.03

oser

0.99

vers

0.95

ze

0.95

zz

0.94

ose

0.93

ppy

0.93

fty

0.93

Activations Density 0.009%

mentions of the term "Lo."

mentions of the name "Lo" in various contexts

No Comments

No Known Activations