INDEX

Explanations

the word "Jet" followed by a number indication

oai_token-act-pair · gpt-3.5-turbo

references to the word "Jet" and its variations 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

\\\\\\\\\\\\\\\\

-0.78

orce

-0.76

ndum

-0.72

 Parables

-0.72

skirts

-0.69

ãģį

-0.68

ACA

-0.67

\\\\\\\\

-0.66

ĻĤ

-0.66

Interstitial

-0.66

POSITIVE LOGITS

Jet

1.22

Jet

1.12

jet

0.92

 Airways

0.90

oleon

0.76

zeb

0.73

Ski

0.72

 Polo

0.69

 propulsion

0.69

 Lines

0.68

Activations Density 0.008%

the word "Jet" followed by a number indication

references to the word "Jet" and its variations in various contexts

No Comments

No Known Activations