INDEX

Explanations

Specific numbers and measurements within text

oai_token-act-pair · gpt-3.5-turbo

various terms that indicate measurements or positions in time or space

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Scrolls

-0.69

glomer

-0.63

 Splash

-0.62

ccording

-0.60

 Embassy

-0.59

iphate

-0.59

 Chronicle

-0.58

 WATCHED

-0.58

 Prosecut

-0.57

 Thousand

-0.56

POSITIVE LOGITS

atown

0.78

 mode

0.73

livion

0.72

zero

0.69

speak

0.68

aturday

0.67

 proportions

0.66

 communism

0.65

 parity

0.65

break

0.65

Activations Density 0.502%

Specific numbers and measurements within text

various terms that indicate measurements or positions in time or space

No Comments

No Known Activations