INDEX

Explanations

words or phrases related to official announcements or declarations

oai_token-act-pair · gpt-3.5-turbo

the word "officially" and its variations indicating formality or confirmation

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

ĸļ

-0.93

wich

-0.76

 Emin

-0.72

 Mong

-0.69

lihood

-0.68

ritch

-0.67

 Prospect

-0.65

ocene

-0.65

vich

-0.65

rug

-0.64

POSITIVE LOGITS

 sanctioned

0.89

dom

0.86

named

0.84

 cleared

0.84

 disbanded

0.82

 declass

0.78

 declared

0.76

 recognised

0.76

ordered

0.74

 recognized

0.74

Activations Density 0.017%

words or phrases related to official announcements or declarations

the word "officially" and its variations indicating formality or confirmation

No Comments

No Known Activations