INDEX

Explanations

occurrences of the word "workshop."

oai_token-act-pair · gpt-3.5-turbo

mentions of workshops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olls

-0.65

ties

-0.65

croft

-0.64

yll

-0.63

sey

-0.61

rises

-0.61

 sovere

-0.61

 earthly

-0.60

sea

-0.59

growth

-0.59

POSITIVE LOGITS

smanship

0.99

 Workshop

0.97

dayName

0.95

 workshop

0.92

ItemTracker

0.90

hops

0.84

 workshops

0.80

workshop

0.80

yrinth

0.79

enegger

0.79

Activations Density 0.008%

occurrences of the word "workshop."

mentions of workshops

No Comments

No Known Activations