INDEX

Explanations

social media handles or usernames

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the letter 'j'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

etheless

-0.76

 avail

-0.63

 formulated

-0.62

AVG

-0.59

ãĤ¼ãĤ¦ãĤ¹

-0.59

ENTS

-0.58

ãĥķãĤ©

-0.58

 Arlington

-0.58

 thyroid

-0.57

 Remastered

-0.57

POSITIVE LOGITS

3.76

je

2.21

jc

2.12

ja

2.07

jer

2.03

jj

2.01

jun

1.94

ju

1.91

jon

1.91

jo

1.90

Activations Density 0.017%

social media handles or usernames

the occurrences of the letter 'j'

No Comments

No Known Activations