INDEX

Explanations

words that end with "une"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "une" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 conduct

-0.64

kg

-0.63

 Carol

-0.62

cou

-0.62

FAC

-0.61

 fiction

-0.60

 medium

-0.60

 carry

-0.59

 Bucs

-0.58

 Photo

-0.58

POSITIVE LOGITS

une

4.79

unes

2.90

UNE

2.60

uned

2.11

uning

1.69

uno

1.56

unity

1.40

una

1.38

uner

1.32

un

1.26

Activations Density 0.013%

words that end with "une"

occurrences of the word "une" and its variations

No Comments

No Known Activations