INDEX

Explanations

phrases related to complexity

oai_token-act-pair · gpt-3.5-turbo

references to complexity in various contexts

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

Bey

-0.72

va

-0.70

endar

-0.70

bed

-0.68

bing

-0.67

ibur

-0.65

enium

-0.64

 corpor

-0.64

 Citizens

-0.63

ovie

-0.62

POSITIVE LOGITS

 Flavoring

0.78

iness

0.78

 richness

0.74

 complexity

0.74

ylum

0.70

externalActionCode

0.69

jriwal

0.69

 cumbers

0.68

iest

0.68

 arises

0.68

Activations Density 0.029%

phrases related to complexity

references to complexity in various contexts

No Comments

No Known Activations