INDEX

Explanations

comparative statements about increasing or decreasing factors

oai_token-act-pair · gpt-3.5-turbo

comparative statements emphasizing the relationship between quantities and outcomes

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

é¾įå

-0.75

osures

-0.72

Dub

-0.66

 john

-0.65

esides

-0.64

hof

-0.63

iet

-0.63

kas

-0.63

utch

-0.63

inth

-0.62

POSITIVE LOGITS

 likely

0.79

achy

0.72

 chance

0.71

 likelihood

0.70

 incentive

0.69

 absorbed

0.69

 surely

0.69

 probability

0.67

 tendency

0.66

 chances

0.66

Activations Density 0.032%

comparative statements about increasing or decreasing factors

comparative statements emphasizing the relationship between quantities and outcomes

No Comments

No Known Activations