INDEX

Explanations

words containing the substring "om" followed by the number 9

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "om"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

++++++++++++++++

-0.70

LIST

-0.70

 Actual

-0.63

Wad

-0.62

lift

-0.60

 Veil

-0.59

 overpower

-0.59

 Kindle

-0.59

 nexus

-0.58

 Brees

-0.58

POSITIVE LOGITS

orrow

1.13

puter

1.12

otive

1.07

obile

1.06

psons

1.00

atoes

0.99

pson

0.96

useum

0.96

puters

0.95

merce

0.94

Activations Density 0.019%

words containing the substring "om" followed by the number 9

mentions of the word "om"

No Comments

No Known Activations