INDEX

Explanations

phrases related to advocating for particular concepts or beliefs

oai_token-act-pair · gpt-3.5-turbo

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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

craft

-0.81

cies

-0.73

mares

-0.71

 besides

-0.69

 writes

-0.68

ells

-0.67

thood

-0.67

fn

-0.67

ersen

-0.67

each

-0.67

POSITIVE LOGITS

 easiest

1.26

 strongest

1.25

 same

1.22

 hardest

1.17

 simplest

1.17

 largest

1.15

 heaviest

1.13

 biggest

1.13

 smallest

1.13

 greatest

1.13

Activations Density 0.251%

phrases related to advocating for particular concepts or beliefs

the word "the."

No Comments

No Known Activations