INDEX

Explanations

mentions of conflicts, wars, and crises

oai_token-act-pair · gpt-3.5-turbo

references to conflicts, particularly wars and crises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

prints

-0.80

mson

-0.78

 Examination

-0.73

 membr

-0.70

asonic

-0.68

 Laboratories

-0.68

redit

-0.68

 copies

-0.67

Magikarp

-0.67

 patents

-0.67

POSITIVE LOGITS

 raging

1.12

 ravaged

1.06

 raged

0.94

 waged

0.89

rav

0.88

 unfolding

0.87

fighting

0.87

 aftermath

0.84

 fighting

0.82

 refugee

0.82

Activations Density 0.100%

mentions of conflicts, wars, and crises

references to conflicts, particularly wars and crises

No Comments

No Known Activations