INDEX

Explanations

phrases indicating quantity or estimation

oai_token-act-pair · gpt-3.5-turbo

phrases that quantify or emphasize large quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

heimer

-0.77

OSE

-0.76

TABLE

-0.74

Kyle

-0.70

lance

-0.69

Gear

-0.68

MD

-0.67

Creat

-0.64

 Peaks

-0.63

UMP

-0.63

POSITIVE LOGITS

 possible

0.95

 practicable

0.89

yip

0.86

pload

0.81

 dozen

0.75

 conceivable

0.74

 Possible

0.70

 imaginable

0.68

ipal

0.66

 hundred

0.65

Activations Density 0.033%

phrases indicating quantity or estimation

phrases that quantify or emphasize large quantities or amounts

No Comments

No Known Activations