INDEX

Explanations

values related to interest rates

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 duplication

-0.77

NetMessage

-0.73

PHOTOS

-0.73

emetery

-0.73

roups

-0.71

 microbi

-0.70

 Folder

-0.70

 Dupl

-0.68

borgh

-0.67

 Span

-0.67

POSITIVE LOGITS

 pegged

1.02

 inflation

1.02

peg

0.98

LIB

0.96

CPI

0.95

ilibrium

0.92

 adjustment

0.90

 deflation

0.90

 lows

0.89

 adjustable

0.89

Activations Density 0.243%

values related to interest rates

No Comments

No Known Activations