INDEX

Explanations

phrases indicating uncertainty or lack of direction

oai_token-act-pair · gpt-3.5-turbo

phrases that express uncertainty or indecision

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

APTER

-0.67

Mur

-0.63

Dur

-0.63

cedented

-0.62

IQ

-0.62

tun

-0.62

Denver

-0.61

Apps

-0.59

drivers

-0.59

quickShipAvailable

-0.58

POSITIVE LOGITS

eat

0.95

 choose

0.93

 treat

0.93

 take

0.91

 celebrate

0.89

 give

0.88

 disperse

0.87

othy

0.87

 interpret

0.85

 pursue

0.84

Activations Density 0.077%

phrases indicating uncertainty or lack of direction

phrases that express uncertainty or indecision

No Comments

No Known Activations