INDEX

Explanations

words related to famous personalities or figures

oai_token-act-pair · gpt-3.5-turbo

specific names or nouns associated with various topics and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 acron

-0.79

 empires

-0.74

ASA

-0.71

ãĥ³ãĤ¸

-0.71

 iPads

-0.68

 Abstract

-0.67

 Defin

-0.66

yout

-0.66

 supers

-0.66

ASP

-0.65

POSITIVE LOGITS

yll

1.05

lem

1.01

ril

1.00

ld

0.99

lay

0.99

ll

0.99

lÃ©

0.99

oll

0.99

leton

0.98

Activations Density 0.204%

words related to famous personalities or figures

specific names or nouns associated with various topics and entities

No Comments

No Known Activations