INDEX

Explanations

acronyms and terms related to financial markets

oai_token-act-pair · gpt-3.5-turbo

references to certain rating systems or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ional

-0.75

bourg

-0.74

burg

-0.74

perse

-0.67

arily

-0.67

mons

-0.63

eers

-0.63

ivities

-0.62

eve

-0.62

orial

-0.61

POSITIVE LOGITS

ounty

1.01

JJ

0.99

axter

0.94

BS

0.93

GV

0.90

BIP

0.89

ANK

0.89

JECT

0.89

ITS

0.88

ruary

0.86

Activations Density 0.091%

acronyms and terms related to financial markets

references to certain rating systems or classifications

No Comments

No Known Activations