INDEX

Explanations

specific names related to politics and possibly international relations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, primarily focusing on the names Zarif and Zam

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãģ®éŃĶ

-0.80

 Camden

-0.76

eredith

-0.74

ITNESS

-0.73

sburgh

-0.73

ÂłÂłÂł

-0.73

é¾įå¥ĳå£«

-0.72

 Armory

-0.68

phis

-0.68

 Seah

-0.68

POSITIVE LOGITS

Zar

1.02

enei

0.85

\\\\\\\\\\\\\\\\

0.78

thal

0.78

imir

0.77

amac

0.77

atos

0.77

assic

0.76

hiba

0.75

quel

0.74

Activations Density 0.012%

specific names related to politics and possibly international relations

mentions of specific individuals, primarily focusing on the names Zarif and Zam

No Comments

No Known Activations