INDEX

Explanations

images or visual content by Getty Images

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Getty Images."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

yip

-0.77

 brill

-0.74

-0.72

 particip

-0.71

jri

-0.71

 infiltr

-0.69

apt

-0.66

lly

-0.64

 privilege

-0.63

kered

-0.63

POSITIVE LOGITS

 Images

2.05

sburg

1.68

Images

1.58

images

1.17

Image

1.05

 Photos

1.01

sburgh

1.00

 Features

1.00

 Image

1.00

 IMAGES

0.99

Activations Density 0.010%

images or visual content by Getty Images

occurrences of the term "Getty Images."

No Comments

No Known Activations