INDEX

Explanations

numerical data points or measurement units in a specific format

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol in the text

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

esses

-0.93

eln

-0.86

rish

-0.85

wagen

-0.78

ement

-0.78

eri

-0.76

etheus

-0.76

aways

-0.75

iane

-0.74

ozy

-0.74

POSITIVE LOGITS

LAB

0.86

 Expand

0.83

Python

0.75

 guiIcon

0.70

CLOSE

0.69

ĸļå£«

0.69

ropolitan

0.69

PDATE

0.68

âĨĳ

0.68

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.67

Activations Density 0.033%

numerical data points or measurement units in a specific format

instances of a specific character or symbol in the text

No Comments

No Known Activations