INDEX

Explanations

dates or specific numbers and measurements

oai_token-act-pair · gpt-3.5-turbo

references to sanctions and related political measures

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

 Guinness

-0.76

Goo

-0.71

Asc

-0.68

canon

-0.68

Ori

-0.65

Ov

-0.65

 Sora

-0.63

 souls

-0.63

é¾įåĸļå£«

-0.63

 Sung

-0.63

POSITIVE LOGITS

 ineffective

0.98

 counterproductive

0.93

 instituted

0.91

 deterrence

0.88

 imposed

0.88

 draconian

0.88

erous

0.85

 defund

0.84

 burdens

0.82

Ĥİ

0.81

Activations Density 0.915%

dates or specific numbers and measurements

references to sanctions and related political measures

No Comments

No Known Activations