INDEX

Explanations

terms related to high levels or degrees of something

oai_token-act-pair · gpt-3.5-turbo

terms associated with high levels or intensities of various factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aws

-0.80

DragonMagazine

-0.78

usr

-0.75

zie

-0.74

alian

-0.73

gu

-0.73

Haunted

-0.73

Theme

-0.71

cour

-0.71

fab

-0.71

POSITIVE LOGITS

(>

1.16

 amounts

1.07

 concentrations

1.05

 susceptibility

0.99

(<

0.96

 quantitative

0.95

 levels

0.94

 doses

0.94

 quantities

0.88

 variability

0.87

Activations Density 0.251%

terms related to high levels or degrees of something

terms associated with high levels or intensities of various factors

No Comments

No Known Activations