INDEX

Explanations

the word "Allah" at varying activation levels

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Abbas."

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

 insured

-0.73

 paycheck

-0.73

 Colossus

-0.71

 disse

-0.69

 Pengu

-0.69

 glim

-0.69

 mammal

-0.68

 unden

-0.66

 ancest

-0.64

 hemor

-0.64

POSITIVE LOGITS

renheit

1.41

aha

1.10

awk

1.03

abad

1.02

ibi

1.01

olics

1.00

tml

0.98

ttp

0.98

abil

0.97

aban

0.96

Activations Density 0.013%

the word "Allah" at varying activation levels

occurrences of the name "Abbas."

No Comments

No Known Activations