INDEX

Explanations

words related to positivity, greatness, and achievement

oai_token-act-pair · gpt-3.5-turbo

variations of the word "treat."

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

BIL

-0.70

OTA

-0.68

BO

-0.66

BOX

-0.65

 Wilde

-0.64

 deleting

-0.64

ItemImage

-0.63

 Lerner

-0.62

PLIC

-0.61

 POLIT

-0.61

POSITIVE LOGITS

htaking

1.12

resses

1.03

idon

1.02

sburg

1.02

iful

1.02

enium

0.98

reat

0.97

acion

0.96

ress

0.95

eous

0.94

Activations Density 0.013%

words related to positivity, greatness, and achievement

variations of the word "treat."

No Comments

No Known Activations