INDEX

Explanations

instances where surveys or polls were conducted

oai_token-act-pair · gpt-3.5-turbo

instances of the word "conducted" in relation to surveys and polls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ulkan

-0.68

mere

-0.64

ãģĦ

-0.60

 Leilan

-0.57

ede

-0.56

ADD

-0.55

Redd

-0.54

hen

-0.53

ãģı

-0.52

RET

-0.52

POSITIVE LOGITS

 jointly

1.06

by

0.97

 anonymously

0.92

 undercover

0.91

 conducted

0.83

 during

0.82

 abroad

0.81

 pursuant

0.79

 annually

0.78

 exclusively

0.78

Activations Density 0.072%

instances where surveys or polls were conducted

instances of the word "conducted" in relation to surveys and polls

No Comments

No Known Activations