INDEX

Explanations

keywords related to names, particularly the name "Rose."

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Rose."

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

ulhu

-0.84

etheless

-0.75

cffff

-0.74

essions

-0.74

oths

-0.69

redit

-0.68

 fragmented

-0.67

ernandez

-0.65

SPONSORED

-0.65

 compuls

-0.63

POSITIVE LOGITS

mary

1.69

anne

1.18

mont

1.12

velt

1.09

water

1.05

hill

1.04

mond

0.98

dale

0.98

Rose

0.98

 Quartz

0.97

Activations Density 0.022%

keywords related to names, particularly the name "Rose."

mentions of the word "Rose."

No Comments

No Known Activations