INDEX

Explanations

dates written in a specific format

oai_token-act-pair · gpt-3.5-turbo

parentheses

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nuts

-0.78

wagen

-0.73

 piping

-0.71

 appropri

-0.69

 gems

-0.68

 everyday

-0.67

 eaves

-0.66

 arbitrarily

-0.65

 orchestr

-0.65

 erect

-0.65

POSITIVE LOGITS

Reuters

1.17

emphasis

1.01

UTERS

0.99

CNN

0.99

Photo

0.99

credit

0.98

Thom

0.98

Courtesy

0.95

written

0.94

updated

0.93

Activations Density 0.033%

dates written in a specific format

parentheses

No Comments

No Known Activations