INDEX

Explanations

experiences or things that attract attention or make an impact

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate attention or impact

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

 latitude

-0.71

 guid

-0.64

clusive

-0.62

ikh

-0.60

ials

-0.59

 stewards

-0.59

ternity

-0.57

lying

-0.56

 ramps

-0.56

bound

-0.56

POSITIVE LOGITS

 viewers

0.77

avorite

0.75

soType

0.71

 audiences

0.67

 alarm

0.67

me

0.66

 nerve

0.66

 nerves

0.65

 reson

0.64

 resonate

0.63

Activations Density 0.302%

experiences or things that attract attention or make an impact

phrases that indicate attention or impact

No Comments

No Known Activations