INDEX

Explanations

the word "NOT" in various contexts

oai_token-act-pair · gpt-3.5-turbo

variations 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 @ 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

stakes

-0.72

 Companies

-0.71

velt

-0.69

eers

-0.66

oise

-0.66

 Tours

-0.63

 Mansion

-0.63

å¤§

-0.62

eur

-0.61

Char

-0.61

POSITIVE LOGITS

epad

1.30

icably

1.22

 necessarily

1.13

orious

1.06

withstanding

1.06

eworthy

1.05

ched

0.92

ices

0.91

ifies

0.91

icable

0.91

Activations Density 0.130%

the word "NOT" in various contexts

variations of the word "not."

No Comments

No Known Activations