INDEX

Explanations

words related to strength, vitality, and energy

oai_token-act-pair · gpt-3.5-turbo

terms related to virulence and various contexts surrounding it

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

uyomi

-0.86

*/(

-0.85

 Unch

-0.75

cedented

-0.73

ĨĴ

-0.72

ļé

-0.72

 quarters

-0.70

ered

-0.69

 Defenders

-0.68

IELD

-0.68

POSITIVE LOGITS

ulent

1.22

ulence

1.20

gil

1.15

gins

1.12

cles

0.94

ted

0.94

lar

0.93

iously

0.93

idium

0.88

idian

0.86

Activations Density 0.010%

words related to strength, vitality, and energy

terms related to virulence and various contexts surrounding it

No Comments

No Known Activations