INDEX

Explanations

the word "do" followed by various other words and contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "do"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

channelAvailability

-0.76

HAEL

-0.67

DragonMagazine

-0.67

 Development

-0.65

ĺħ

-0.63

 Nieto

-0.63

 Translation

-0.62

ĸļ

-0.61

Seb

-0.61

£ı

-0.60

POSITIVE LOGITS

able

0.87

ables

0.86

aways

0.84

isp

0.84

auc

0.82

ork

0.81

away

0.81

liest

0.80

iled

0.79

rib

0.79

Activations Density 0.090%

the word "do" followed by various other words and contexts

instances of the word "do"

No Comments

No Known Activations