INDEX

Explanations

prepositions followed by nouns

oai_token-act-pair · gpt-3.5-turbo

actions and phrases related to inquiries and solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

soType

-0.67

Engineers

-0.62

acan

-0.62

eni

-0.60

atsuki

-0.58

caster

-0.58

ãĥĦ

-0.57

REF

-0.55

IRO

-0.55

bane

-0.54

POSITIVE LOGITS

 these

1.76

these

1.45

 those

1.38

These

1.29

 THESE

1.25

 them

1.25

 These

1.21

those

1.11

 each

1.10

 ones

1.09

Activations Density 0.769%

prepositions followed by nouns

actions and phrases related to inquiries and solutions

No Comments

No Known Activations