INDEX

Explanations

mentions of a specific entity or person named "Murabaha"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Murabaha."

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

 Pixie

-0.75

 Gutenberg

-0.71

ISM

-0.68

 Bermuda

-0.68

 Wester

-0.67

 WARN

-0.66

 Primal

-0.66

 Celest

-0.65

 Clarkson

-0.65

BOOK

-0.64

POSITIVE LOGITS

mur

1.23

geon

1.02

rats

0.98

nit

0.96

daq

0.95

anda

0.93

uj

0.93

phys

0.93

phies

0.92

abit

0.91

Activations Density 0.008%

mentions of a specific entity or person named "Murabaha"

mentions of the name "Murabaha."

No Comments

No Known Activations