INDEX

Explanations

words related to medical conditions or terms ending in 'en'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "en-" in various words

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

DragonMagazine

-1.00

TPPStreamerBot

-0.72

ĳå£«

-0.71

 CEOs

-0.67

 Palmer

-0.66

ramid

-0.64

 Dare

-0.64

 Heights

-0.63

 directors

-0.63

ocene

-0.63

POSITIVE LOGITS

viron

1.33

joined

1.05

unci

1.04

semb

1.04

forcer

1.01

 masse

0.99

ounter

0.99

quire

0.97

chanted

0.97

cyclop

0.96

Activations Density 0.012%

words related to medical conditions or terms ending in 'en'

occurrences of the prefix "en-" in various words

No Comments

No Known Activations