INDEX

Explanations

personal interactions with the speaker being referred to

oai_token-act-pair · gpt-3.5-turbo

instances of the word "me."

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

 Equality

-0.68

earable

-0.64

 Compliance

-0.62

 Pric

-0.61

raviolet

-0.61

 tide

-0.61

profits

-0.60

 Centers

-0.60

 tides

-0.59

Us

-0.59

POSITIVE LOGITS

zzo

1.12

adows

1.09

adow

1.02

 personally

1.01

lees

0.97

imei

0.96

andering

0.91

cca

0.87

gal

0.80

zz

0.80

Activations Density 0.097%

personal interactions with the speaker being referred to

instances of the word "me."

No Comments

No Known Activations