INDEX

Explanations

terms related to political news and events

oai_token-act-pair · gpt-3.5-turbo

events related to political actions and statements

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

 glim

-0.71

 mould

-0.71

 proble

-0.70

.","

-0.68

 lapt

-0.66

 realise

-0.66

ktop

-0.66

catentry

-0.65

idae

-0.65

loo

-0.64

POSITIVE LOGITS

 Obama

1.10

 Congressional

1.06

 Congressman

1.03

 MSNBC

1.03

 McCain

1.03

 Senator

1.02

 Republican

1.01

 congressional

1.01

 Benghazi

1.00

Obama

0.99

Activations Density 1.212%

terms related to political news and events

events related to political actions and statements

No Comments

No Known Activations