INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

a specific character or symbol that appears frequently 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 favour

-0.83

 favor

-0.83

 reflex

-0.81

 clitor

-0.79

 grazing

-0.76

 morph

-0.76

 phon

-0.71

 purported

-0.70

 division

-0.69

 territorial

-0.69

POSITIVE LOGITS

ï¸ı

1.16

Because

1.01

there

1.00

Otherwise

0.98

It

0.95

Therefore

0.94

Companies

0.92

They

0.92

Secondly

0.90

But

0.89

Activations Density 0.125%

proper nouns or names

a specific character or symbol that appears frequently in the text

No Comments

No Known Activations