INDEX

Explanations

various mentions of technical tasks and operations involving the term "work"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "work" and its variations in a computing 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

 Flavoring

-0.78

xual

-0.74

antha

-0.74

Jed

-0.72

 Shal

-0.69

 Ukrain

-0.69

 Gord

-0.68

gars

-0.67

rition

-0.66

iren

-0.65

POSITIVE LOGITS

station

1.11

flows

1.11

bench

1.02

paces

0.87

papers

0.86

heet

0.86

hops

0.85

river

0.81

 arrang

0.77

Area

0.74

Activations Density 0.074%

various mentions of technical tasks and operations involving the term "work"

instances of the word "work" and its variations in a computing context

No Comments

No Known Activations