INDEX

Explanations

terms related to negation, primarily the word "Not."

oai_token-act-pair · gpt-3.5-turbo

negations or instances of the word "not."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

stakes

-0.81

velt

-0.79

ç·

-0.70

assetsadobe

-0.65

hower

-0.62

æ©

-0.60

 Quarterly

-0.60

 contrasts

-0.60

å¤§

-0.60

kamp

-0.60

POSITIVE LOGITS

epad

1.24

icably

1.17

orious

1.12

ifications

1.12

eworthy

1.11

withstanding

1.09

ifier

1.04

 necessarily

1.02

ional

1.00

ices

1.00

Activations Density 0.084%

terms related to negation, primarily the word "Not."

negations or instances of the word "not."

No Comments

No Known Activations