INDEX

Explanations

the word "joke" followed by either the number 9 or 10

oai_token-act-pair · gpt-3.5-turbo

the concept of "joke" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

undai

-0.71

phalt

-0.67

ignty

-0.67

ignt

-0.66

EVA

-0.64

actions

-0.64

enture

-0.63

ills

-0.63

CLASSIFIED

-0.63

arnaev

-0.62

POSITIVE LOGITS

ously

1.14

 jokes

0.93

osal

0.83

 joking

0.82

 mocking

0.81

bag

0.79

sters

0.79

writer

0.78

 joke

0.77

bags

0.76

Activations Density 0.049%

the word "joke" followed by either the number 9 or 10

the concept of "joke" in various contexts

No Comments

No Known Activations