INDEX

Explanations

words related to strong negative emotions or conflicts

oai_token-act-pair · gpt-3.5-turbo

words associated with rancor and fractiousness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Atlantis

-0.69

 Doctrine

-0.67

 Gravity

-0.64

 Fore

-0.64

 PowerPoint

-0.63

 Archdemon

-0.62

 Scotia

-0.62

uyomi

-0.61

 Expand

-0.61

 Reading

-0.59

POSITIVE LOGITS

 ranc

1.14

ÃŃa

0.87

 corrid

0.85

yssey

0.82

aste

0.82

hers

0.80

anth

0.80

esse

0.80

iously

0.80

 lapt

0.79

Activations Density 0.008%

words related to strong negative emotions or conflicts

words associated with rancor and fractiousness

No Comments

No Known Activations