INDEX

Explanations

references to specific entities or organizations, such as treaty names or company names

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "the."

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

 besides

-0.79

leeve

-0.77

 communicates

-0.71

ature

-0.68

 publishes

-0.68

 resembles

-0.68

 solves

-0.67

 Edited

-0.67

 illustrates

-0.67

atures

-0.66

POSITIVE LOGITS

 aforementioned

1.28

 slightest

1.14

 entirety

1.00

 smallest

0.98

 infamous

0.97

 latter

0.96

 occasional

0.92

 latest

0.92

 dreaded

0.91

 likes

0.89

Activations Density 0.280%

references to specific entities or organizations, such as treaty names or company names

repeated instances of the word "the."

No Comments

No Known Activations