INDEX

Explanations

comparisons indicating superiority or advantage of one thing over another

oai_token-act-pair · gpt-3.5-turbo

comparative phrases that highlight superiority in features or benefits, particularly in technology or products

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ô

-0.79

fecture

-0.73

FontSize

-0.70

arta

-0.67

Putin

-0.65

undo

-0.65

Cause

-0.63

_-_

-0.63

................................................................

-0.63

Brew

-0.63

POSITIVE LOGITS

 conventional

1.32

 traditional

1.31

 alternatives

1.15

 existing

1.10

 comparable

1.03

 ordinary

1.00

 bulky

0.97

 standard

0.96

 regular

0.94

traditional

0.94

Activations Density 0.232%

comparisons indicating superiority or advantage of one thing over another

comparative phrases that highlight superiority in features or benefits, particularly in technology or products

No Comments

No Known Activations