INDEX

Explanations

mentions of aid-related terms such as "aid groups," "aid workers," and "aid organizations."

oai_token-act-pair · gpt-3.5-turbo

references to humanitarian aid and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Beard

-0.96

âĸ¬

-0.82

beard

-0.76

 Bellev

-0.70

 hairs

-0.70

nen

-0.68

Face

-0.66

juries

-0.65

 repet

-0.65

 Athletic

-0.65

POSITIVE LOGITS

aid

1.06

 treaty

0.94

 embargo

0.91

 treaties

0.88

 convoy

0.87

giving

0.84

 flows

0.83

 supplies

0.82

 agencies

0.81

 shipments

0.80

Activations Density 0.036%

mentions of aid-related terms such as "aid groups," "aid workers," and "aid organizations."

references to humanitarian aid and organizations

No Comments

No Known Activations