INDEX

Explanations

text related to people's names, especially "Catherine" and "Shepard."

oai_token-act-pair · gpt-3.5-turbo

the name "Catherine" and its variations in context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lasses

-0.94

oard

-0.83

keye

-0.82

yip

-0.78

lass

-0.76

eties

-0.75

rities

-0.74

oras

-0.74

lux

-0.74

orage

-0.74

POSITIVE LOGITS

ICAL

0.69

 Weed

0.69

FUL

0.67

 Reincarnated

0.66

Dialogue

0.64

 Mechdragon

0.62

ically

0.62

iano

0.60

 Benz

0.60

lain

0.60

Activations Density 0.064%

text related to people's names, especially "Catherine" and "Shepard."

the name "Catherine" and its variations in context

No Comments

No Known Activations