INDEX

Explanations

references to smaller entities in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "smaller" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ILLE

-0.81

Maps

-0.72

SEA

-0.70

onso

-0.70

elf

-0.70

plain

-0.69

Storm

-0.69

shire

-0.68

RA

-0.67

EP

-0.66

POSITIVE LOGITS

 sized

1.09

 than

1.05

 intestine

0.95

 diameter

0.90

 Than

0.88

than

0.88

 eleph

0.87

 stature

0.86

 fractions

0.83

pox

0.79

Activations Density 0.022%

references to smaller entities in various contexts

mentions of the term "smaller" in various contexts

No Comments

No Known Activations