INDEX

Explanations

the word "legitimacy" and variations of it

oai_token-act-pair · gpt-3.5-turbo

the use of the word "illegitimate."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 destro

-0.85

NetMessage

-0.73

 therap

-0.73

¥ŀ

-0.71

SPONSORED

-0.71

 schooling

-0.70

«ĺ

-0.68

Ļ½

-0.66

ĻĤ

-0.66

©¶æ

-0.66

POSITIVE LOGITS

uary

1.08

anium

1.07

amins

1.02

chell

1.00

ocracy

0.99

ariat

0.98

rogen

0.92

ople

0.92

onal

0.92

atis

0.90

Activations Density 0.041%

the word "legitimacy" and variations of it

the use of the word "illegitimate."

No Comments

No Known Activations