INDEX

Explanations

statements asking for or acknowledging additional information or content

oai_token-act-pair · gpt-3.5-turbo

references to an increase or abundance of something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xtap

-1.08

Enlarge

-0.73

ĺħ

-0.69

Guard

-0.67

liest

-0.66

atan

-0.65

Ń·

-0.65

ube

-0.64

ļé

-0.64

Gra

-0.63

POSITIVE LOGITS

 than

1.34

ado

1.12

 Than

0.98

 stringent

0.93

 importantly

0.87

than

0.87

natureconservancy

0.85

 sophisticated

0.82

 information

0.80

 manageable

0.78

Activations Density 0.147%

statements asking for or acknowledging additional information or content

references to an increase or abundance of something

No Comments

No Known Activations