INDEX

Explanations

words with the prefix "en-" followed by a verb or a noun

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "en-"

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

DragonMagazine

-0.91

ĳå£«

-0.74

TPPStreamerBot

-0.74

 Palmer

-0.68

ramid

-0.66

 Dare

-0.63

ocene

-0.63

ioxide

-0.63

 Murd

-0.63

hyde

-0.61

POSITIVE LOGITS

viron

1.36

semb

1.08

igma

1.08

unci

1.07

chanted

1.05

joined

1.05

cyclop

1.02

 masse

1.01

quire

1.01

forcer

0.99

Activations Density 0.014%

words with the prefix "en-" followed by a verb or a noun

occurrences of the prefix "en-"

No Comments

No Known Activations