INDEX

Explanations

phrases indicating comparison, disagreement, or commentary on shared views

oai_token-act-pair · gpt-3.5-turbo

phrases indicating reference to a group or category

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

 disposed

-0.65

 istg

-0.63

wise

-0.63

 notwithstanding

-0.62

 Donation

-0.62

 Password

-0.62

 parcel

-0.62

 ende

-0.61

peed

-0.60

 Referred

-0.60

POSITIVE LOGITS

them

0.76

their

0.70

udes

0.67

us

0.66

 humanity

0.65

 those

0.65

those

0.65

arching

0.65

ĳå£«

0.64

our

0.64

Activations Density 0.140%

phrases indicating comparison, disagreement, or commentary on shared views

phrases indicating reference to a group or category

No Comments

No Known Activations