INDEX

Explanations

numbers and measurements

oai_token-act-pair · gpt-3.5-turbo

expressions of quantity or measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Dialogue

-0.70

 compliments

-0.69

 Divinity

-0.62

tyr

-0.61

 glim

-0.60

 Protector

-0.59

 sacrific

-0.59

 Legions

-0.59

)].

-0.59

 loneliness

-0.59

POSITIVE LOGITS

azeera

0.83

ãĥĳ

0.81

ãĥķãĤ©

0.78

odox

0.75

ãĥĥãĥĪ

0.74

vier

0.73

reet

0.72

utterstock

0.72

ãĥ«

0.71

uously

0.69

Activations Density 0.794%

numbers and measurements

expressions of quantity or measurement

No Comments

No Known Activations