INDEX

Explanations

mentions of political controversy or conflict

oai_token-act-pair · gpt-3.5-turbo

instances of negativity or criticism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 detached

-0.76

 Sakuya

-0.76

 guiActiveUnfocused

-0.75

 Eisen

-0.72

 Niet

-0.70

 fragmentation

-0.68

 Sapphire

-0.68

 mosqu

-0.68

 Elys

-0.64

 bombard

-0.64

POSITIVE LOGITS

ł

1.12

Ĳ

1.10

¹

1.08

ª

1.08

ĳ

1.03

£

1.00

Ĵ

0.99

ı

0.97

âĸº

0.97

¸

0.93

Activations Density 0.200%

mentions of political controversy or conflict

instances of negativity or criticism

No Comments

No Known Activations