INDEX

Explanations

references to specific titles or positions of authority

oai_token-act-pair · gpt-3.5-turbo

references to positions or titles related to leadership, specifically in governmental or intelligence agencies

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

VALUE

-0.79

MpServer

-0.75

np

-0.69

english

-0.67

learning

-0.67

alle

-0.67

gro

-0.66

worldly

-0.66

wcsstore

-0.65

à¤

-0.63

POSITIVE LOGITS

anamo

0.83

 Julius

0.77

arette

0.75

 Brett

0.74

gerald

0.72

 Jerome

0.71

 Sonny

0.70

 Gina

0.69

 nomine

0.69

 Patty

0.68

Activations Density 0.065%

references to specific titles or positions of authority

references to positions or titles related to leadership, specifically in governmental or intelligence agencies

No Comments

No Known Activations