INDEX

Explanations

proper nouns related to political entities or organizations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

isable

-0.74

FUL

-0.69

jad

-0.67

 Pose

-0.65

prising

-0.63

estamp

-0.62

onga

-0.61

NetMessage

-0.61

LV

-0.60

issan

-0.60

POSITIVE LOGITS

 inspector

1.21

 Inspector

1.19

 bureaucracy

0.97

 Accountability

0.96

IG

0.95

 Correspond

0.92

 Office

0.89

 bureaucrats

0.87

 contractor

0.86

 secretaries

0.85

Activations Density 0.072%

proper nouns related to political entities or organizations

No Comments

No Known Activations