INDEX

Explanations

phrases related to being equipped with various items or technologies

oai_token-act-pair · gpt-3.5-turbo

references to items or entities that are equipped or furnished with specific features or tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

asta

-0.67

rase

-0.66

 Decay

-0.64

grave

-0.63

birth

-0.61

mary

-0.60

apers

-0.59

analysis

-0.59

zeb

-0.59

ctrl

-0.59

POSITIVE LOGITS

fitted

0.88

 equipped

0.74

 with

0.73

ged

0.70

iterranean

0.69

 fitted

0.69

ments

0.68

ioned

0.67

 accordingly

0.65

nesses

0.64

Activations Density 0.092%

phrases related to being equipped with various items or technologies

references to items or entities that are equipped or furnished with specific features or tools

No Comments

No Known Activations