INDEX

Explanations

words related to physical damage

oai_token-act-pair · gpt-3.5-turbo

references to damage and its impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

zsche

-0.80

zee

-0.78

uesday

-0.69

zbek

-0.69

ramid

-0.69

 Reloaded

-0.67

unin

-0.64

guyen

-0.64

rams

-0.64

liner

-0.63

POSITIVE LOGITS

 inflicted

1.18

 wrought

1.00

 damage

0.96

 mitigation

0.94

damage

0.88

 sustained

0.82

 caused

0.81

 damaged

0.80

 incurred

0.79

 done

0.78

Activations Density 0.042%

words related to physical damage

references to damage and its impact

No Comments

No Known Activations