INDEX

Explanations

proper nouns or specific terms

oai_token-act-pair · gpt-3.5-turbo

specific brand names or notable entities

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

shapeshifter

-0.72

 subscribed

-0.67

EStream

-0.66

psey

-0.65

isSpecialOrderable

-0.65

 apiece

-0.64

DOE

-0.63

lain

-0.62

staking

-0.62

bye

-0.62

POSITIVE LOGITS

itions

0.86

tones

0.81

atures

0.79

uctions

0.76

vironments

0.74

ombat

0.74

rus

0.72

ancers

0.72

ieties

0.71

ancer

0.69

Activations Density 0.487%

proper nouns or specific terms

specific brand names or notable entities

No Comments

No Known Activations