INDEX

Explanations

keywords related to international relations, politics, and possibly conflicts

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

relationships involving emotional and mental states or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 helicop

-1.05

 cooker

-0.99

 stalk

-0.94

 scraping

-0.93

 streaming

-0.93

 burner

-0.93

 sleeper

-0.91

 blitz

-0.91

 platinum

-0.90

 taxi

-0.90

POSITIVE LOGITS

 Belief

1.63

 Responsibility

1.58

 Influence

1.57

 Choice

1.54

 Interpret

1.54

 Accuracy

1.52

 Desire

1.51

 Sense

1.51

 Relations

1.51

Mis

1.50

Activations Density 0.299%

keywords related to international relations, politics, and possibly conflicts

relationships involving emotional and mental states or conditions

No Comments

No Known Activations