INDEX

Explanations

phrases conveying absence or restriction

oai_token-act-pair · gpt-3.5-turbo

instances of the word "no" and its context, indicating negation or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

su

-0.78

Tsu

-0.71

emin

-0.69

hurst

-0.65

Su

-0.65

 Fusion

-0.63

stand

-0.62

Join

-0.62

 Shan

-0.61

Notes

-0.60

POSITIVE LOGITS

inventoryQuantity

0.66

 embassies

0.64

 slightest

0.63

etc

0.60

 corrid

0.59

 clot

0.59

trak

0.59

asso

0.58

hews

0.57

staking

0.57

Activations Density 0.379%

phrases conveying absence or restriction

instances of the word "no" and its context, indicating negation or absence

No Comments

No Known Activations