INDEX

Explanations

phrases related to people coming in to take action

oai_token-act-pair · gpt-3.5-turbo

instances of coordination or connection between actions or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ictions

-0.73

chance

-0.62

ansk

-0.60

 centr

-0.60

 Nept

-0.58

ongo

-0.57

acci

-0.57

ung

-0.56

altern

-0.56

until

-0.56

POSITIVE LOGITS

wre

0.95

 greet

0.86

 greeted

0.80

 greets

0.79

 bite

0.71

 slay

0.69

 demanded

0.68

 apologized

0.67

 promptly

0.67

ocide

0.66

Activations Density 0.244%

phrases related to people coming in to take action

instances of coordination or connection between actions or subjects

No Comments

No Known Activations