INDEX

Explanations

measurements or quantifiable units

oai_token-act-pair · gpt-3.5-turbo

references to units of measurement or military units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

vous

-0.74

fter

-0.73

issance

-0.70

lli

-0.69

aukee

-0.67

cape

-0.67

 acknow

-0.65

 volunt

-0.65

lla

-0.65

byss

-0.65

POSITIVE LOGITS

mate

0.99

mates

0.95

ary

0.89

aries

0.85

arily

0.81

agers

0.80

rity

0.78

aged

0.78

imet

0.77

 units

0.77

Activations Density 0.031%

measurements or quantifiable units

references to units of measurement or military units

No Comments

No Known Activations