INDEX

Explanations

words related to various groupings of people or entities

oai_token-act-pair · gpt-3.5-turbo

terms related to various groups or categories of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Flavoring

-0.68

FontSize

-0.68

;;;;;;;;;;;;

-0.63

lighting

-0.62

eous

-0.56

Translation

-0.55

Sharp

-0.54

staking

-0.54

âĶĢâĶĢâĶĢâĶĢ

-0.51

 Boat

-0.51

POSITIVE LOGITS

are

1.45

 were

1.39

 aren

1.22

 weren

1.18

ARE

1.15

 have

1.09

 arrive

1.07

 exist

1.07

were

1.06

 appear

1.06

Activations Density 0.412%

words related to various groupings of people or entities

terms related to various groups or categories of people

No Comments

No Known Activations