INDEX

Explanations

phrases describing a quantity or a specific group of items

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to categories, instances, or classes of items or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

abus

-0.80

osate

-0.77

Spoiler

-0.74

uberty

-0.71

endon

-0.71

slaught

-0.70

 Canaver

-0.69

obook

-0.69

rium

-0.69

isconsin

-0.69

POSITIVE LOGITS

 things

1.05

 items

1.00

 types

0.99

 kinds

0.99

 pesky

0.96

 occasions

0.95

 entities

0.95

 cases

0.95

 situations

0.94

 categories

0.94

Activations Density 0.109%

phrases describing a quantity or a specific group of items

phrases that refer to categories, instances, or classes of items or experiences

No Comments

No Known Activations