INDEX

Explanations

words related to technology, specifically referencing technology names and terms like "Micronesia."

oai_token-act-pair · gpt-3.5-turbo

references to "Micron" and associated derivatives, particularly in a technical or product context

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

tenance

-0.66

 Spectre

-0.66

ACTED

-0.66

istically

-0.65

DragonMagazine

-0.64

ĪĴ

-0.63

ãģĤ

-0.63

Interstitial

-0.62

ãģĮ

-0.62

POSITIVE LOGITS

onductor

1.03

HAEL

1.03

onduct

0.90

ropolitan

0.89

olon

0.89

achu

0.89

rones

0.88

plates

0.84

ron

0.83

oleon

0.82

Activations Density 0.023%

words related to technology, specifically referencing technology names and terms like "Micronesia."

references to "Micron" and associated derivatives, particularly in a technical or product context

No Comments

No Known Activations