INDEX

Explanations

words related to file encryption formats

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics related to various topics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 creature

-0.68

 lifes

-0.64

swe

-0.64

 reflex

-0.64

 incarn

-0.63

 daily

-0.63

 lawfully

-0.62

 endeav

-0.61

 covenant

-0.61

 emoji

-0.61

POSITIVE LOGITS

Meanwhile

1.24

Advertisement

1.21

However

1.18

Instead

1.17

Since

1.17

According

1.16

Related

1.15

Some

1.15

ccording

1.15

Also

1.15

Activations Density 0.702%

words related to file encryption formats

numerical data or statistics related to various topics

No Comments

No Known Activations