INDEX

Explanations

phrases or comparisons using the word "as."

oai_token-act-pair · gpt-3.5-turbo

expressions that compare or equate two subjects using "as."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¥

-0.69

DIT

-0.68

TAIN

-0.66

ASE

-0.66

SHIP

-0.64

 VIDEOS

-0.64

NEY

-0.64

OUR

-0.64

åĪ

-0.63

GES

-0.59

POSITIVE LOGITS

pired

1.17

bestos

1.05

pires

1.03

phalt

1.01

part

1.00

par

0.93

phy

0.93

ylum

0.92

piring

0.90

 usual

0.88

Activations Density 0.184%

phrases or comparisons using the word "as."

expressions that compare or equate two subjects using "as."

No Comments

No Known Activations