INDEX

Explanations

phrases related to security breaches

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically commas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĢħ

-0.71

VERTISEMENT

-0.70

IQ

-0.66

ISE

-0.66

enter

-0.63

isure

-0.63

onica

-0.61

à¥

-0.60

itto

-0.60

itory

-0.60

POSITIVE LOGITS

 nevertheless

1.05

Downloadha

0.94

 fortunately

0.82

 nonetheless

0.75

 anecd

0.73

 thankfully

0.69

 luckily

0.69

 alas

0.69

 insofar

0.67

mercial

0.65

Activations Density 0.229%

phrases related to security breaches

punctuation marks, specifically commas

No Comments

No Known Activations