INDEX

Explanations

phrases indicating something or someone can benefit from a particular action

oai_token-act-pair · gpt-3.5-turbo

phrases indicating potential benefits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

soDeliveryDate

-0.83

channelAvailability

-0.72

fing

-0.69

 Firefly

-0.69

IFE

-0.67

sf

-0.66

Nap

-0.66

utical

-0.65

earchers

-0.65

Jess

-0.65

POSITIVE LOGITS

 hindsight

0.73

 riches

0.71

Reward

0.67

lihood

0.67

 cures

0.65

 taxpayer

0.63

aea

0.62

 exploiting

0.62

 outweigh

0.61

ierrez

0.61

Activations Density 0.161%

phrases indicating something or someone can benefit from a particular action

phrases indicating potential benefits

No Comments

No Known Activations