INDEX

Explanations

references to locations or locations mentioned in a factual context

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and special characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ARCH

-0.62

ore

-0.60

orer

-0.59

oir

-0.58

phan

-0.57

ocial

-0.56

NK

-0.56

 Hampton

-0.55

oner

-0.55

ites

-0.55

POSITIVE LOGITS

 respectively

0.95

etc

0.71

drivers

0.70

 namely

0.68

but

0.67

 whereas

0.66

FontSize

0.66

 although

0.65

 culminating

0.65

0.64

Activations Density 0.479%

references to locations or locations mentioned in a factual context

punctuation marks and special characters

No Comments

No Known Activations